upload rlrb_bs128_nobuf (8/8)
Browse files- .gitattributes +4 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_750/config.json +67 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_750/eval_metrics.json +1146 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_750/generation_config.json +6 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_750/merges.txt +0 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_750/model-00001-of-00002.safetensors +3 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_750/model-00002-of-00002.safetensors +3 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_750/model.safetensors.index.json +443 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_750/special_tokens_map.json +31 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_750/tokenizer.json +3 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_750/tokenizer_config.json +207 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_750/vocab.json +0 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_800/added_tokens.json +24 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_800/chat_template.jinja +54 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_800/config.json +67 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_800/eval_metrics.json +1148 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_800/generation_config.json +6 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_800/merges.txt +0 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_800/model-00001-of-00002.safetensors +3 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_800/model-00002-of-00002.safetensors +3 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_800/model.safetensors.index.json +443 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_800/special_tokens_map.json +31 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_800/tokenizer.json +3 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_800/tokenizer_config.json +207 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_800/vocab.json +0 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_900/added_tokens.json +24 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_900/chat_template.jinja +54 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_900/config.json +67 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_900/generation_config.json +6 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_900/merges.txt +0 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_900/model-00001-of-00002.safetensors +3 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_900/model-00002-of-00002.safetensors +3 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_900/model.safetensors.index.json +443 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_900/special_tokens_map.json +31 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_900/tokenizer.json +3 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_900/tokenizer_config.json +207 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_900/vocab.json +0 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_950/added_tokens.json +24 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_950/chat_template.jinja +54 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_950/config.json +67 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_950/generation_config.json +6 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_950/merges.txt +0 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_950/model-00001-of-00002.safetensors +3 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_950/model-00002-of-00002.safetensors +3 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_950/model.safetensors.index.json +443 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_950/special_tokens_map.json +31 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_950/tokenizer.json +3 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_950/tokenizer_config.json +207 -0
- rlrb_bs128_nobuf/checkpoints_hf_format/global_step_950/vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -124,3 +124,7 @@ rlrb_bs128_nobuf/checkpoints_hf_format/global_step_550/tokenizer.json filter=lfs
|
|
| 124 |
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 125 |
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_650/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 126 |
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 124 |
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 125 |
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_650/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 126 |
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 127 |
+
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_750/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 128 |
+
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 129 |
+
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 130 |
+
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_950/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_750/config.json
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"dtype": "bfloat16",
|
| 7 |
+
"eos_token_id": 151643,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 2048,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 11008,
|
| 12 |
+
"layer_types": [
|
| 13 |
+
"full_attention",
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention"
|
| 49 |
+
],
|
| 50 |
+
"max_position_embeddings": 32768,
|
| 51 |
+
"max_window_layers": 36,
|
| 52 |
+
"model_type": "qwen2",
|
| 53 |
+
"num_attention_heads": 16,
|
| 54 |
+
"num_hidden_layers": 36,
|
| 55 |
+
"num_key_value_heads": 2,
|
| 56 |
+
"pad_token_id": 151643,
|
| 57 |
+
"rms_norm_eps": 1e-06,
|
| 58 |
+
"rope_scaling": null,
|
| 59 |
+
"rope_theta": 1000000.0,
|
| 60 |
+
"sliding_window": null,
|
| 61 |
+
"tie_word_embeddings": true,
|
| 62 |
+
"transformers_version": "4.57.6",
|
| 63 |
+
"use_cache": true,
|
| 64 |
+
"use_mrope": false,
|
| 65 |
+
"use_sliding_window": false,
|
| 66 |
+
"vocab_size": 151936
|
| 67 |
+
}
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_750/eval_metrics.json
ADDED
|
@@ -0,0 +1,1146 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"global_step": 750,
|
| 3 |
+
"ckpt_dir": "/mnt/mystorageoutput/projects/jy_intern/amlt-results/7213899235.25497-028989ec-3fee/qwen3b_kk_rlrb_bs128_nobuf/checkpoints_hf_format/global_step_750",
|
| 4 |
+
"rollouts_dir": "/mnt/mystorageoutput/projects/jy_intern/amlt-results/7213899235.25497-028989ec-3fee/qwen3b_kk_rlrb_bs128_nobuf/rollouts/training",
|
| 5 |
+
"init_model_path": "Qwen/Qwen2.5-3B",
|
| 6 |
+
"prev_step": null,
|
| 7 |
+
"positive_score": 1.0,
|
| 8 |
+
"negative_score": 0.0,
|
| 9 |
+
"history_step_stride": 25,
|
| 10 |
+
"max_samples_per_class": 0,
|
| 11 |
+
"in_batch": {
|
| 12 |
+
"num_records": 1024,
|
| 13 |
+
"source_steps": [
|
| 14 |
+
750
|
| 15 |
+
],
|
| 16 |
+
"num_source_steps": 1,
|
| 17 |
+
"num_positives_pre_cap": 453,
|
| 18 |
+
"num_negatives_pre_cap": 571,
|
| 19 |
+
"positive": {
|
| 20 |
+
"loss": 0.45325678729953195,
|
| 21 |
+
"token_entropy": 0.022797478501887576,
|
| 22 |
+
"num_supervised_tokens": 168318,
|
| 23 |
+
"kl_from_init": 3.3278250386672754,
|
| 24 |
+
"kl_to_init": 0.35545366028163466,
|
| 25 |
+
"dead_units": {
|
| 26 |
+
"layer_0": {
|
| 27 |
+
"intermediate_size": 11008,
|
| 28 |
+
"dead_count": 0,
|
| 29 |
+
"dead_fraction": 0.0,
|
| 30 |
+
"mean_activation_freq": 0.9235875144202061,
|
| 31 |
+
"min_activation_freq": 0.7821979823904752
|
| 32 |
+
},
|
| 33 |
+
"layer_1": {
|
| 34 |
+
"intermediate_size": 11008,
|
| 35 |
+
"dead_count": 8841,
|
| 36 |
+
"dead_fraction": 0.8031431686046512,
|
| 37 |
+
"mean_activation_freq": 0.14743887871469483,
|
| 38 |
+
"min_activation_freq": 0.0
|
| 39 |
+
},
|
| 40 |
+
"layer_2": {
|
| 41 |
+
"intermediate_size": 11008,
|
| 42 |
+
"dead_count": 7474,
|
| 43 |
+
"dead_fraction": 0.6789607558139535,
|
| 44 |
+
"mean_activation_freq": 0.1664064564933085,
|
| 45 |
+
"min_activation_freq": 0.0
|
| 46 |
+
},
|
| 47 |
+
"layer_3": {
|
| 48 |
+
"intermediate_size": 11008,
|
| 49 |
+
"dead_count": 412,
|
| 50 |
+
"dead_fraction": 0.037427325581395346,
|
| 51 |
+
"mean_activation_freq": 0.38553146744727657,
|
| 52 |
+
"min_activation_freq": 0.0
|
| 53 |
+
},
|
| 54 |
+
"layer_4": {
|
| 55 |
+
"intermediate_size": 11008,
|
| 56 |
+
"dead_count": 23,
|
| 57 |
+
"dead_fraction": 0.0020893895348837207,
|
| 58 |
+
"mean_activation_freq": 0.5480919687992993,
|
| 59 |
+
"min_activation_freq": 0.0
|
| 60 |
+
},
|
| 61 |
+
"layer_5": {
|
| 62 |
+
"intermediate_size": 11008,
|
| 63 |
+
"dead_count": 7,
|
| 64 |
+
"dead_fraction": 0.0006359011627906977,
|
| 65 |
+
"mean_activation_freq": 0.7149102855333772,
|
| 66 |
+
"min_activation_freq": 0.0
|
| 67 |
+
},
|
| 68 |
+
"layer_6": {
|
| 69 |
+
"intermediate_size": 11008,
|
| 70 |
+
"dead_count": 0,
|
| 71 |
+
"dead_fraction": 0.0,
|
| 72 |
+
"mean_activation_freq": 0.869979923690781,
|
| 73 |
+
"min_activation_freq": 0.0948324005751019
|
| 74 |
+
},
|
| 75 |
+
"layer_7": {
|
| 76 |
+
"intermediate_size": 11008,
|
| 77 |
+
"dead_count": 0,
|
| 78 |
+
"dead_fraction": 0.0,
|
| 79 |
+
"mean_activation_freq": 0.8846149474912451,
|
| 80 |
+
"min_activation_freq": 0.033430767951140104
|
| 81 |
+
},
|
| 82 |
+
"layer_8": {
|
| 83 |
+
"intermediate_size": 11008,
|
| 84 |
+
"dead_count": 0,
|
| 85 |
+
"dead_fraction": 0.0,
|
| 86 |
+
"mean_activation_freq": 0.9413034146053001,
|
| 87 |
+
"min_activation_freq": 0.08650292897966944
|
| 88 |
+
},
|
| 89 |
+
"layer_9": {
|
| 90 |
+
"intermediate_size": 11008,
|
| 91 |
+
"dead_count": 0,
|
| 92 |
+
"dead_fraction": 0.0,
|
| 93 |
+
"mean_activation_freq": 0.9493722788003094,
|
| 94 |
+
"min_activation_freq": 0.2516961941087703
|
| 95 |
+
},
|
| 96 |
+
"layer_10": {
|
| 97 |
+
"intermediate_size": 11008,
|
| 98 |
+
"dead_count": 0,
|
| 99 |
+
"dead_fraction": 0.0,
|
| 100 |
+
"mean_activation_freq": 0.9738937207891307,
|
| 101 |
+
"min_activation_freq": 0.6803372188357751
|
| 102 |
+
},
|
| 103 |
+
"layer_11": {
|
| 104 |
+
"intermediate_size": 11008,
|
| 105 |
+
"dead_count": 0,
|
| 106 |
+
"dead_fraction": 0.0,
|
| 107 |
+
"mean_activation_freq": 0.9851206491719579,
|
| 108 |
+
"min_activation_freq": 0.9345702776886607
|
| 109 |
+
},
|
| 110 |
+
"layer_12": {
|
| 111 |
+
"intermediate_size": 11008,
|
| 112 |
+
"dead_count": 0,
|
| 113 |
+
"dead_fraction": 0.0,
|
| 114 |
+
"mean_activation_freq": 0.9867980872549662,
|
| 115 |
+
"min_activation_freq": 0.921969129861334
|
| 116 |
+
},
|
| 117 |
+
"layer_13": {
|
| 118 |
+
"intermediate_size": 11008,
|
| 119 |
+
"dead_count": 0,
|
| 120 |
+
"dead_fraction": 0.0,
|
| 121 |
+
"mean_activation_freq": 0.9808055267695465,
|
| 122 |
+
"min_activation_freq": 0.8957211944058271
|
| 123 |
+
},
|
| 124 |
+
"layer_14": {
|
| 125 |
+
"intermediate_size": 11008,
|
| 126 |
+
"dead_count": 0,
|
| 127 |
+
"dead_fraction": 0.0,
|
| 128 |
+
"mean_activation_freq": 0.9830454054541558,
|
| 129 |
+
"min_activation_freq": 0.8914316947682364
|
| 130 |
+
},
|
| 131 |
+
"layer_15": {
|
| 132 |
+
"intermediate_size": 11008,
|
| 133 |
+
"dead_count": 0,
|
| 134 |
+
"dead_fraction": 0.0,
|
| 135 |
+
"mean_activation_freq": 0.9802573663729881,
|
| 136 |
+
"min_activation_freq": 0.9044249575208831
|
| 137 |
+
},
|
| 138 |
+
"layer_16": {
|
| 139 |
+
"intermediate_size": 11008,
|
| 140 |
+
"dead_count": 0,
|
| 141 |
+
"dead_fraction": 0.0,
|
| 142 |
+
"mean_activation_freq": 0.9795600957875072,
|
| 143 |
+
"min_activation_freq": 0.9020187977518744
|
| 144 |
+
},
|
| 145 |
+
"layer_17": {
|
| 146 |
+
"intermediate_size": 11008,
|
| 147 |
+
"dead_count": 0,
|
| 148 |
+
"dead_fraction": 0.0,
|
| 149 |
+
"mean_activation_freq": 0.9794714477676115,
|
| 150 |
+
"min_activation_freq": 0.9179113344977959
|
| 151 |
+
},
|
| 152 |
+
"layer_18": {
|
| 153 |
+
"intermediate_size": 11008,
|
| 154 |
+
"dead_count": 0,
|
| 155 |
+
"dead_fraction": 0.0,
|
| 156 |
+
"mean_activation_freq": 0.9799149005130999,
|
| 157 |
+
"min_activation_freq": 0.9240841740039687
|
| 158 |
+
},
|
| 159 |
+
"layer_19": {
|
| 160 |
+
"intermediate_size": 11008,
|
| 161 |
+
"dead_count": 0,
|
| 162 |
+
"dead_fraction": 0.0,
|
| 163 |
+
"mean_activation_freq": 0.9769697780970447,
|
| 164 |
+
"min_activation_freq": 0.9145664753621122
|
| 165 |
+
},
|
| 166 |
+
"layer_20": {
|
| 167 |
+
"intermediate_size": 11008,
|
| 168 |
+
"dead_count": 0,
|
| 169 |
+
"dead_fraction": 0.0,
|
| 170 |
+
"mean_activation_freq": 0.9794848002099846,
|
| 171 |
+
"min_activation_freq": 0.9099799189629155
|
| 172 |
+
},
|
| 173 |
+
"layer_21": {
|
| 174 |
+
"intermediate_size": 11008,
|
| 175 |
+
"dead_count": 0,
|
| 176 |
+
"dead_fraction": 0.0,
|
| 177 |
+
"mean_activation_freq": 0.9796269648620883,
|
| 178 |
+
"min_activation_freq": 0.9209591368718735
|
| 179 |
+
},
|
| 180 |
+
"layer_22": {
|
| 181 |
+
"intermediate_size": 11008,
|
| 182 |
+
"dead_count": 0,
|
| 183 |
+
"dead_fraction": 0.0,
|
| 184 |
+
"mean_activation_freq": 0.979407364679592,
|
| 185 |
+
"min_activation_freq": 0.9276666785489371
|
| 186 |
+
},
|
| 187 |
+
"layer_23": {
|
| 188 |
+
"intermediate_size": 11008,
|
| 189 |
+
"dead_count": 0,
|
| 190 |
+
"dead_fraction": 0.0,
|
| 191 |
+
"mean_activation_freq": 0.9795879545737002,
|
| 192 |
+
"min_activation_freq": 0.9395786546893381
|
| 193 |
+
},
|
| 194 |
+
"layer_24": {
|
| 195 |
+
"intermediate_size": 11008,
|
| 196 |
+
"dead_count": 0,
|
| 197 |
+
"dead_fraction": 0.0,
|
| 198 |
+
"mean_activation_freq": 0.981656298090381,
|
| 199 |
+
"min_activation_freq": 0.9285697311042195
|
| 200 |
+
},
|
| 201 |
+
"layer_25": {
|
| 202 |
+
"intermediate_size": 11008,
|
| 203 |
+
"dead_count": 0,
|
| 204 |
+
"dead_fraction": 0.0,
|
| 205 |
+
"mean_activation_freq": 0.9837133767656225,
|
| 206 |
+
"min_activation_freq": 0.9495597618792999
|
| 207 |
+
},
|
| 208 |
+
"layer_26": {
|
| 209 |
+
"intermediate_size": 11008,
|
| 210 |
+
"dead_count": 0,
|
| 211 |
+
"dead_fraction": 0.0,
|
| 212 |
+
"mean_activation_freq": 0.9856755904935758,
|
| 213 |
+
"min_activation_freq": 0.9559405411185969
|
| 214 |
+
},
|
| 215 |
+
"layer_27": {
|
| 216 |
+
"intermediate_size": 11008,
|
| 217 |
+
"dead_count": 0,
|
| 218 |
+
"dead_fraction": 0.0,
|
| 219 |
+
"mean_activation_freq": 0.9869053207520468,
|
| 220 |
+
"min_activation_freq": 0.9421274017039176
|
| 221 |
+
},
|
| 222 |
+
"layer_28": {
|
| 223 |
+
"intermediate_size": 11008,
|
| 224 |
+
"dead_count": 0,
|
| 225 |
+
"dead_fraction": 0.0,
|
| 226 |
+
"mean_activation_freq": 0.9872669835813274,
|
| 227 |
+
"min_activation_freq": 0.21370857543459404
|
| 228 |
+
},
|
| 229 |
+
"layer_29": {
|
| 230 |
+
"intermediate_size": 11008,
|
| 231 |
+
"dead_count": 0,
|
| 232 |
+
"dead_fraction": 0.0,
|
| 233 |
+
"mean_activation_freq": 0.9884800276045177,
|
| 234 |
+
"min_activation_freq": 0.9600280421582956
|
| 235 |
+
},
|
| 236 |
+
"layer_30": {
|
| 237 |
+
"intermediate_size": 11008,
|
| 238 |
+
"dead_count": 0,
|
| 239 |
+
"dead_fraction": 0.0,
|
| 240 |
+
"mean_activation_freq": 0.9900361462812501,
|
| 241 |
+
"min_activation_freq": 0.5407264820161837
|
| 242 |
+
},
|
| 243 |
+
"layer_31": {
|
| 244 |
+
"intermediate_size": 11008,
|
| 245 |
+
"dead_count": 0,
|
| 246 |
+
"dead_fraction": 0.0,
|
| 247 |
+
"mean_activation_freq": 0.990910520769518,
|
| 248 |
+
"min_activation_freq": 0.9425432811701661
|
| 249 |
+
},
|
| 250 |
+
"layer_32": {
|
| 251 |
+
"intermediate_size": 11008,
|
| 252 |
+
"dead_count": 0,
|
| 253 |
+
"dead_fraction": 0.0,
|
| 254 |
+
"mean_activation_freq": 0.9890807741720614,
|
| 255 |
+
"min_activation_freq": 0.5043192053137514
|
| 256 |
+
},
|
| 257 |
+
"layer_33": {
|
| 258 |
+
"intermediate_size": 11008,
|
| 259 |
+
"dead_count": 0,
|
| 260 |
+
"dead_fraction": 0.0,
|
| 261 |
+
"mean_activation_freq": 0.9869938360031139,
|
| 262 |
+
"min_activation_freq": 0.9253555769436425
|
| 263 |
+
},
|
| 264 |
+
"layer_34": {
|
| 265 |
+
"intermediate_size": 11008,
|
| 266 |
+
"dead_count": 0,
|
| 267 |
+
"dead_fraction": 0.0,
|
| 268 |
+
"mean_activation_freq": 0.9881469888711829,
|
| 269 |
+
"min_activation_freq": 0.886417376632327
|
| 270 |
+
},
|
| 271 |
+
"layer_35": {
|
| 272 |
+
"intermediate_size": 11008,
|
| 273 |
+
"dead_count": 0,
|
| 274 |
+
"dead_fraction": 0.0,
|
| 275 |
+
"mean_activation_freq": 0.9918065975641829,
|
| 276 |
+
"min_activation_freq": 0.007200655901329627
|
| 277 |
+
},
|
| 278 |
+
"_overall": {
|
| 279 |
+
"dead_count": 16757,
|
| 280 |
+
"intermediate_total": 396288,
|
| 281 |
+
"dead_fraction": 0.04228490390826874
|
| 282 |
+
}
|
| 283 |
+
},
|
| 284 |
+
"size": 453,
|
| 285 |
+
"size_pre_filter": 453,
|
| 286 |
+
"skipped_long": 0
|
| 287 |
+
},
|
| 288 |
+
"negative": {
|
| 289 |
+
"loss": 0.4100134591283212,
|
| 290 |
+
"token_entropy": 0.021796946699098624,
|
| 291 |
+
"num_supervised_tokens": 247590,
|
| 292 |
+
"kl_from_init": 3.1038108498740358,
|
| 293 |
+
"kl_to_init": 0.3386095654122341,
|
| 294 |
+
"dead_units": {
|
| 295 |
+
"layer_0": {
|
| 296 |
+
"intermediate_size": 11008,
|
| 297 |
+
"dead_count": 0,
|
| 298 |
+
"dead_fraction": 0.0,
|
| 299 |
+
"mean_activation_freq": 0.9240783973639606,
|
| 300 |
+
"min_activation_freq": 0.7826204612464154
|
| 301 |
+
},
|
| 302 |
+
"layer_1": {
|
| 303 |
+
"intermediate_size": 11008,
|
| 304 |
+
"dead_count": 8832,
|
| 305 |
+
"dead_fraction": 0.8023255813953488,
|
| 306 |
+
"mean_activation_freq": 0.14721590514830407,
|
| 307 |
+
"min_activation_freq": 0.0
|
| 308 |
+
},
|
| 309 |
+
"layer_2": {
|
| 310 |
+
"intermediate_size": 11008,
|
| 311 |
+
"dead_count": 4136,
|
| 312 |
+
"dead_fraction": 0.3757267441860465,
|
| 313 |
+
"mean_activation_freq": 0.16631032858793657,
|
| 314 |
+
"min_activation_freq": 0.0
|
| 315 |
+
},
|
| 316 |
+
"layer_3": {
|
| 317 |
+
"intermediate_size": 11008,
|
| 318 |
+
"dead_count": 323,
|
| 319 |
+
"dead_fraction": 0.029342296511627907,
|
| 320 |
+
"mean_activation_freq": 0.3855395441562476,
|
| 321 |
+
"min_activation_freq": 0.0
|
| 322 |
+
},
|
| 323 |
+
"layer_4": {
|
| 324 |
+
"intermediate_size": 11008,
|
| 325 |
+
"dead_count": 16,
|
| 326 |
+
"dead_fraction": 0.0014534883720930232,
|
| 327 |
+
"mean_activation_freq": 0.552293104436653,
|
| 328 |
+
"min_activation_freq": 0.0
|
| 329 |
+
},
|
| 330 |
+
"layer_5": {
|
| 331 |
+
"intermediate_size": 11008,
|
| 332 |
+
"dead_count": 4,
|
| 333 |
+
"dead_fraction": 0.0003633720930232558,
|
| 334 |
+
"mean_activation_freq": 0.7174159317330695,
|
| 335 |
+
"min_activation_freq": 0.0
|
| 336 |
+
},
|
| 337 |
+
"layer_6": {
|
| 338 |
+
"intermediate_size": 11008,
|
| 339 |
+
"dead_count": 0,
|
| 340 |
+
"dead_fraction": 0.0,
|
| 341 |
+
"mean_activation_freq": 0.8720936638790968,
|
| 342 |
+
"min_activation_freq": 0.09792802617230098
|
| 343 |
+
},
|
| 344 |
+
"layer_7": {
|
| 345 |
+
"intermediate_size": 11008,
|
| 346 |
+
"dead_count": 0,
|
| 347 |
+
"dead_fraction": 0.0,
|
| 348 |
+
"mean_activation_freq": 0.8865057412908107,
|
| 349 |
+
"min_activation_freq": 0.04291368795185589
|
| 350 |
+
},
|
| 351 |
+
"layer_8": {
|
| 352 |
+
"intermediate_size": 11008,
|
| 353 |
+
"dead_count": 0,
|
| 354 |
+
"dead_fraction": 0.0,
|
| 355 |
+
"mean_activation_freq": 0.941743213076969,
|
| 356 |
+
"min_activation_freq": 0.0849993941596995
|
| 357 |
+
},
|
| 358 |
+
"layer_9": {
|
| 359 |
+
"intermediate_size": 11008,
|
| 360 |
+
"dead_count": 0,
|
| 361 |
+
"dead_fraction": 0.0,
|
| 362 |
+
"mean_activation_freq": 0.9501064484009573,
|
| 363 |
+
"min_activation_freq": 0.26198957954683144
|
| 364 |
+
},
|
| 365 |
+
"layer_10": {
|
| 366 |
+
"intermediate_size": 11008,
|
| 367 |
+
"dead_count": 0,
|
| 368 |
+
"dead_fraction": 0.0,
|
| 369 |
+
"mean_activation_freq": 0.9741517872553038,
|
| 370 |
+
"min_activation_freq": 0.6813078072620057
|
| 371 |
+
},
|
| 372 |
+
"layer_11": {
|
| 373 |
+
"intermediate_size": 11008,
|
| 374 |
+
"dead_count": 0,
|
| 375 |
+
"dead_fraction": 0.0,
|
| 376 |
+
"mean_activation_freq": 0.9850777068703934,
|
| 377 |
+
"min_activation_freq": 0.9329334787350054
|
| 378 |
+
},
|
| 379 |
+
"layer_12": {
|
| 380 |
+
"intermediate_size": 11008,
|
| 381 |
+
"dead_count": 0,
|
| 382 |
+
"dead_fraction": 0.0,
|
| 383 |
+
"mean_activation_freq": 0.986771501621562,
|
| 384 |
+
"min_activation_freq": 0.9199361848216809
|
| 385 |
+
},
|
| 386 |
+
"layer_13": {
|
| 387 |
+
"intermediate_size": 11008,
|
| 388 |
+
"dead_count": 0,
|
| 389 |
+
"dead_fraction": 0.0,
|
| 390 |
+
"mean_activation_freq": 0.9806958792057763,
|
| 391 |
+
"min_activation_freq": 0.8973544973544973
|
| 392 |
+
},
|
| 393 |
+
"layer_14": {
|
| 394 |
+
"intermediate_size": 11008,
|
| 395 |
+
"dead_count": 0,
|
| 396 |
+
"dead_fraction": 0.0,
|
| 397 |
+
"mean_activation_freq": 0.9829867154103935,
|
| 398 |
+
"min_activation_freq": 0.8916999878831939
|
| 399 |
+
},
|
| 400 |
+
"layer_15": {
|
| 401 |
+
"intermediate_size": 11008,
|
| 402 |
+
"dead_count": 0,
|
| 403 |
+
"dead_fraction": 0.0,
|
| 404 |
+
"mean_activation_freq": 0.980183229046027,
|
| 405 |
+
"min_activation_freq": 0.9064461407972858
|
| 406 |
+
},
|
| 407 |
+
"layer_16": {
|
| 408 |
+
"intermediate_size": 11008,
|
| 409 |
+
"dead_count": 0,
|
| 410 |
+
"dead_fraction": 0.0,
|
| 411 |
+
"mean_activation_freq": 0.9795234784250406,
|
| 412 |
+
"min_activation_freq": 0.9024072054606406
|
| 413 |
+
},
|
| 414 |
+
"layer_17": {
|
| 415 |
+
"intermediate_size": 11008,
|
| 416 |
+
"dead_count": 0,
|
| 417 |
+
"dead_fraction": 0.0,
|
| 418 |
+
"mean_activation_freq": 0.9794200375779492,
|
| 419 |
+
"min_activation_freq": 0.9190556969182924
|
| 420 |
+
},
|
| 421 |
+
"layer_18": {
|
| 422 |
+
"intermediate_size": 11008,
|
| 423 |
+
"dead_count": 0,
|
| 424 |
+
"dead_fraction": 0.0,
|
| 425 |
+
"mean_activation_freq": 0.979910998273355,
|
| 426 |
+
"min_activation_freq": 0.9213780847368633
|
| 427 |
+
},
|
| 428 |
+
"layer_19": {
|
| 429 |
+
"intermediate_size": 11008,
|
| 430 |
+
"dead_count": 0,
|
| 431 |
+
"dead_fraction": 0.0,
|
| 432 |
+
"mean_activation_freq": 0.9769378292935762,
|
| 433 |
+
"min_activation_freq": 0.9153560321499252
|
| 434 |
+
},
|
| 435 |
+
"layer_20": {
|
| 436 |
+
"intermediate_size": 11008,
|
| 437 |
+
"dead_count": 0,
|
| 438 |
+
"dead_fraction": 0.0,
|
| 439 |
+
"mean_activation_freq": 0.9794807551629099,
|
| 440 |
+
"min_activation_freq": 0.9124964659315804
|
| 441 |
+
},
|
| 442 |
+
"layer_21": {
|
| 443 |
+
"intermediate_size": 11008,
|
| 444 |
+
"dead_count": 0,
|
| 445 |
+
"dead_fraction": 0.0,
|
| 446 |
+
"mean_activation_freq": 0.9795149976881792,
|
| 447 |
+
"min_activation_freq": 0.9223191566703017
|
| 448 |
+
},
|
| 449 |
+
"layer_22": {
|
| 450 |
+
"intermediate_size": 11008,
|
| 451 |
+
"dead_count": 0,
|
| 452 |
+
"dead_fraction": 0.0,
|
| 453 |
+
"mean_activation_freq": 0.9792063023887485,
|
| 454 |
+
"min_activation_freq": 0.9283573649985863
|
| 455 |
+
},
|
| 456 |
+
"layer_23": {
|
| 457 |
+
"intermediate_size": 11008,
|
| 458 |
+
"dead_count": 0,
|
| 459 |
+
"dead_fraction": 0.0,
|
| 460 |
+
"mean_activation_freq": 0.9792843538601655,
|
| 461 |
+
"min_activation_freq": 0.9377680843329698
|
| 462 |
+
},
|
| 463 |
+
"layer_24": {
|
| 464 |
+
"intermediate_size": 11008,
|
| 465 |
+
"dead_count": 0,
|
| 466 |
+
"dead_fraction": 0.0,
|
| 467 |
+
"mean_activation_freq": 0.9814428305434152,
|
| 468 |
+
"min_activation_freq": 0.9303041318308494
|
| 469 |
+
},
|
| 470 |
+
"layer_25": {
|
| 471 |
+
"intermediate_size": 11008,
|
| 472 |
+
"dead_count": 0,
|
| 473 |
+
"dead_fraction": 0.0,
|
| 474 |
+
"mean_activation_freq": 0.9834631934699339,
|
| 475 |
+
"min_activation_freq": 0.9498243063128559
|
| 476 |
+
},
|
| 477 |
+
"layer_26": {
|
| 478 |
+
"intermediate_size": 11008,
|
| 479 |
+
"dead_count": 0,
|
| 480 |
+
"dead_fraction": 0.0,
|
| 481 |
+
"mean_activation_freq": 0.9854662397547239,
|
| 482 |
+
"min_activation_freq": 0.9552485964699705
|
| 483 |
+
},
|
| 484 |
+
"layer_27": {
|
| 485 |
+
"intermediate_size": 11008,
|
| 486 |
+
"dead_count": 0,
|
| 487 |
+
"dead_fraction": 0.0,
|
| 488 |
+
"mean_activation_freq": 0.9867001003775231,
|
| 489 |
+
"min_activation_freq": 0.9397431237125894
|
| 490 |
+
},
|
| 491 |
+
"layer_28": {
|
| 492 |
+
"intermediate_size": 11008,
|
| 493 |
+
"dead_count": 0,
|
| 494 |
+
"dead_fraction": 0.0,
|
| 495 |
+
"mean_activation_freq": 0.9870905815491571,
|
| 496 |
+
"min_activation_freq": 0.21641423320812633
|
| 497 |
+
},
|
| 498 |
+
"layer_29": {
|
| 499 |
+
"intermediate_size": 11008,
|
| 500 |
+
"dead_count": 0,
|
| 501 |
+
"dead_fraction": 0.0,
|
| 502 |
+
"mean_activation_freq": 0.9883106423539195,
|
| 503 |
+
"min_activation_freq": 0.9583424209378407
|
| 504 |
+
},
|
| 505 |
+
"layer_30": {
|
| 506 |
+
"intermediate_size": 11008,
|
| 507 |
+
"dead_count": 0,
|
| 508 |
+
"dead_fraction": 0.0,
|
| 509 |
+
"mean_activation_freq": 0.9899075998879195,
|
| 510 |
+
"min_activation_freq": 0.5518114624984853
|
| 511 |
+
},
|
| 512 |
+
"layer_31": {
|
| 513 |
+
"intermediate_size": 11008,
|
| 514 |
+
"dead_count": 0,
|
| 515 |
+
"dead_fraction": 0.0,
|
| 516 |
+
"mean_activation_freq": 0.9908092687196434,
|
| 517 |
+
"min_activation_freq": 0.9437255139545215
|
| 518 |
+
},
|
| 519 |
+
"layer_32": {
|
| 520 |
+
"intermediate_size": 11008,
|
| 521 |
+
"dead_count": 0,
|
| 522 |
+
"dead_fraction": 0.0,
|
| 523 |
+
"mean_activation_freq": 0.9889459491239737,
|
| 524 |
+
"min_activation_freq": 0.48954723534876204
|
| 525 |
+
},
|
| 526 |
+
"layer_33": {
|
| 527 |
+
"intermediate_size": 11008,
|
| 528 |
+
"dead_count": 0,
|
| 529 |
+
"dead_fraction": 0.0,
|
| 530 |
+
"mean_activation_freq": 0.9868486934249656,
|
| 531 |
+
"min_activation_freq": 0.9235308372712953
|
| 532 |
+
},
|
| 533 |
+
"layer_34": {
|
| 534 |
+
"intermediate_size": 11008,
|
| 535 |
+
"dead_count": 0,
|
| 536 |
+
"dead_fraction": 0.0,
|
| 537 |
+
"mean_activation_freq": 0.9879802249352362,
|
| 538 |
+
"min_activation_freq": 0.8880164788561735
|
| 539 |
+
},
|
| 540 |
+
"layer_35": {
|
| 541 |
+
"intermediate_size": 11008,
|
| 542 |
+
"dead_count": 0,
|
| 543 |
+
"dead_fraction": 0.0,
|
| 544 |
+
"mean_activation_freq": 0.9920652191046103,
|
| 545 |
+
"min_activation_freq": 0.00969748374328527
|
| 546 |
+
},
|
| 547 |
+
"_overall": {
|
| 548 |
+
"dead_count": 13311,
|
| 549 |
+
"intermediate_total": 396288,
|
| 550 |
+
"dead_fraction": 0.03358920784883721
|
| 551 |
+
}
|
| 552 |
+
},
|
| 553 |
+
"size": 571,
|
| 554 |
+
"size_pre_filter": 571,
|
| 555 |
+
"skipped_long": 0
|
| 556 |
+
}
|
| 557 |
+
},
|
| 558 |
+
"old_data": {
|
| 559 |
+
"num_records": 29696,
|
| 560 |
+
"source_steps": [
|
| 561 |
+
25,
|
| 562 |
+
50,
|
| 563 |
+
75,
|
| 564 |
+
100,
|
| 565 |
+
125,
|
| 566 |
+
150,
|
| 567 |
+
175,
|
| 568 |
+
200,
|
| 569 |
+
225,
|
| 570 |
+
250,
|
| 571 |
+
275,
|
| 572 |
+
300,
|
| 573 |
+
325,
|
| 574 |
+
350,
|
| 575 |
+
375,
|
| 576 |
+
400,
|
| 577 |
+
425,
|
| 578 |
+
450,
|
| 579 |
+
475,
|
| 580 |
+
500,
|
| 581 |
+
525,
|
| 582 |
+
550,
|
| 583 |
+
575,
|
| 584 |
+
600,
|
| 585 |
+
625,
|
| 586 |
+
650,
|
| 587 |
+
675,
|
| 588 |
+
700,
|
| 589 |
+
725
|
| 590 |
+
],
|
| 591 |
+
"num_source_steps": 29,
|
| 592 |
+
"num_positives_pre_cap": 11182,
|
| 593 |
+
"num_negatives_pre_cap": 18514,
|
| 594 |
+
"positive": {
|
| 595 |
+
"loss": 1.007671607083234,
|
| 596 |
+
"token_entropy": 0.02704707161933118,
|
| 597 |
+
"num_supervised_tokens": 4034365,
|
| 598 |
+
"kl_from_init": 3.3517877829672726,
|
| 599 |
+
"kl_to_init": 0.40386673940401824,
|
| 600 |
+
"dead_units": {
|
| 601 |
+
"layer_0": {
|
| 602 |
+
"intermediate_size": 11008,
|
| 603 |
+
"dead_count": 0,
|
| 604 |
+
"dead_fraction": 0.0,
|
| 605 |
+
"mean_activation_freq": 0.9236409677552496,
|
| 606 |
+
"min_activation_freq": 0.7823667417301112
|
| 607 |
+
},
|
| 608 |
+
"layer_1": {
|
| 609 |
+
"intermediate_size": 11008,
|
| 610 |
+
"dead_count": 8758,
|
| 611 |
+
"dead_fraction": 0.7956031976744186,
|
| 612 |
+
"mean_activation_freq": 0.14752479760438367,
|
| 613 |
+
"min_activation_freq": 0.0
|
| 614 |
+
},
|
| 615 |
+
"layer_2": {
|
| 616 |
+
"intermediate_size": 11008,
|
| 617 |
+
"dead_count": 2530,
|
| 618 |
+
"dead_fraction": 0.2298328488372093,
|
| 619 |
+
"mean_activation_freq": 0.16654144499671847,
|
| 620 |
+
"min_activation_freq": 0.0
|
| 621 |
+
},
|
| 622 |
+
"layer_3": {
|
| 623 |
+
"intermediate_size": 11008,
|
| 624 |
+
"dead_count": 41,
|
| 625 |
+
"dead_fraction": 0.003724563953488372,
|
| 626 |
+
"mean_activation_freq": 0.38746605023289166,
|
| 627 |
+
"min_activation_freq": 0.0
|
| 628 |
+
},
|
| 629 |
+
"layer_4": {
|
| 630 |
+
"intermediate_size": 11008,
|
| 631 |
+
"dead_count": 1,
|
| 632 |
+
"dead_fraction": 9.084302325581395e-05,
|
| 633 |
+
"mean_activation_freq": 0.5535227988667001,
|
| 634 |
+
"min_activation_freq": 0.0
|
| 635 |
+
},
|
| 636 |
+
"layer_5": {
|
| 637 |
+
"intermediate_size": 11008,
|
| 638 |
+
"dead_count": 0,
|
| 639 |
+
"dead_fraction": 0.0,
|
| 640 |
+
"mean_activation_freq": 0.7154895556691742,
|
| 641 |
+
"min_activation_freq": 1.0162689791330234e-05
|
| 642 |
+
},
|
| 643 |
+
"layer_6": {
|
| 644 |
+
"intermediate_size": 11008,
|
| 645 |
+
"dead_count": 0,
|
| 646 |
+
"dead_fraction": 0.0,
|
| 647 |
+
"mean_activation_freq": 0.869883986066984,
|
| 648 |
+
"min_activation_freq": 0.08933400919351621
|
| 649 |
+
},
|
| 650 |
+
"layer_7": {
|
| 651 |
+
"intermediate_size": 11008,
|
| 652 |
+
"dead_count": 0,
|
| 653 |
+
"dead_fraction": 0.0,
|
| 654 |
+
"mean_activation_freq": 0.8851711626475237,
|
| 655 |
+
"min_activation_freq": 0.03277690541138445
|
| 656 |
+
},
|
| 657 |
+
"layer_8": {
|
| 658 |
+
"intermediate_size": 11008,
|
| 659 |
+
"dead_count": 0,
|
| 660 |
+
"dead_fraction": 0.0,
|
| 661 |
+
"mean_activation_freq": 0.9409224336583661,
|
| 662 |
+
"min_activation_freq": 0.08933624002786066
|
| 663 |
+
},
|
| 664 |
+
"layer_9": {
|
| 665 |
+
"intermediate_size": 11008,
|
| 666 |
+
"dead_count": 0,
|
| 667 |
+
"dead_fraction": 0.0,
|
| 668 |
+
"mean_activation_freq": 0.9485708946932271,
|
| 669 |
+
"min_activation_freq": 0.2556045375170566
|
| 670 |
+
},
|
| 671 |
+
"layer_10": {
|
| 672 |
+
"intermediate_size": 11008,
|
| 673 |
+
"dead_count": 0,
|
| 674 |
+
"dead_fraction": 0.0,
|
| 675 |
+
"mean_activation_freq": 0.9732503352907632,
|
| 676 |
+
"min_activation_freq": 0.6650528645772011
|
| 677 |
+
},
|
| 678 |
+
"layer_11": {
|
| 679 |
+
"intermediate_size": 11008,
|
| 680 |
+
"dead_count": 0,
|
| 681 |
+
"dead_fraction": 0.0,
|
| 682 |
+
"mean_activation_freq": 0.9850991983346187,
|
| 683 |
+
"min_activation_freq": 0.9331577584080767
|
| 684 |
+
},
|
| 685 |
+
"layer_12": {
|
| 686 |
+
"intermediate_size": 11008,
|
| 687 |
+
"dead_count": 0,
|
| 688 |
+
"dead_fraction": 0.0,
|
| 689 |
+
"mean_activation_freq": 0.9867655031286948,
|
| 690 |
+
"min_activation_freq": 0.9204846363678052
|
| 691 |
+
},
|
| 692 |
+
"layer_13": {
|
| 693 |
+
"intermediate_size": 11008,
|
| 694 |
+
"dead_count": 0,
|
| 695 |
+
"dead_fraction": 0.0,
|
| 696 |
+
"mean_activation_freq": 0.9807647351877501,
|
| 697 |
+
"min_activation_freq": 0.9003982039304823
|
| 698 |
+
},
|
| 699 |
+
"layer_14": {
|
| 700 |
+
"intermediate_size": 11008,
|
| 701 |
+
"dead_count": 0,
|
| 702 |
+
"dead_fraction": 0.0,
|
| 703 |
+
"mean_activation_freq": 0.982998197661845,
|
| 704 |
+
"min_activation_freq": 0.8967681407111157
|
| 705 |
+
},
|
| 706 |
+
"layer_15": {
|
| 707 |
+
"intermediate_size": 11008,
|
| 708 |
+
"dead_count": 0,
|
| 709 |
+
"dead_fraction": 0.0,
|
| 710 |
+
"mean_activation_freq": 0.9802374444170259,
|
| 711 |
+
"min_activation_freq": 0.9090456614609735
|
| 712 |
+
},
|
| 713 |
+
"layer_16": {
|
| 714 |
+
"intermediate_size": 11008,
|
| 715 |
+
"dead_count": 0,
|
| 716 |
+
"dead_fraction": 0.0,
|
| 717 |
+
"mean_activation_freq": 0.9795772943470125,
|
| 718 |
+
"min_activation_freq": 0.9079426378128901
|
| 719 |
+
},
|
| 720 |
+
"layer_17": {
|
| 721 |
+
"intermediate_size": 11008,
|
| 722 |
+
"dead_count": 0,
|
| 723 |
+
"dead_fraction": 0.0,
|
| 724 |
+
"mean_activation_freq": 0.9794852692328473,
|
| 725 |
+
"min_activation_freq": 0.9209102299866274
|
| 726 |
+
},
|
| 727 |
+
"layer_18": {
|
| 728 |
+
"intermediate_size": 11008,
|
| 729 |
+
"dead_count": 0,
|
| 730 |
+
"dead_fraction": 0.0,
|
| 731 |
+
"mean_activation_freq": 0.9799169148499899,
|
| 732 |
+
"min_activation_freq": 0.9255813492333986
|
| 733 |
+
},
|
| 734 |
+
"layer_19": {
|
| 735 |
+
"intermediate_size": 11008,
|
| 736 |
+
"dead_count": 0,
|
| 737 |
+
"dead_fraction": 0.0,
|
| 738 |
+
"mean_activation_freq": 0.9769428294918909,
|
| 739 |
+
"min_activation_freq": 0.9177446760518695
|
| 740 |
+
},
|
| 741 |
+
"layer_20": {
|
| 742 |
+
"intermediate_size": 11008,
|
| 743 |
+
"dead_count": 0,
|
| 744 |
+
"dead_fraction": 0.0,
|
| 745 |
+
"mean_activation_freq": 0.9794547312876447,
|
| 746 |
+
"min_activation_freq": 0.9095552831734363
|
| 747 |
+
},
|
| 748 |
+
"layer_21": {
|
| 749 |
+
"intermediate_size": 11008,
|
| 750 |
+
"dead_count": 0,
|
| 751 |
+
"dead_fraction": 0.0,
|
| 752 |
+
"mean_activation_freq": 0.9796371699750435,
|
| 753 |
+
"min_activation_freq": 0.9237257907997913
|
| 754 |
+
},
|
| 755 |
+
"layer_22": {
|
| 756 |
+
"intermediate_size": 11008,
|
| 757 |
+
"dead_count": 0,
|
| 758 |
+
"dead_fraction": 0.0,
|
| 759 |
+
"mean_activation_freq": 0.9794516423863959,
|
| 760 |
+
"min_activation_freq": 0.9290845027656149
|
| 761 |
+
},
|
| 762 |
+
"layer_23": {
|
| 763 |
+
"intermediate_size": 11008,
|
| 764 |
+
"dead_count": 0,
|
| 765 |
+
"dead_fraction": 0.0,
|
| 766 |
+
"mean_activation_freq": 0.9796299528188264,
|
| 767 |
+
"min_activation_freq": 0.9388000342061267
|
| 768 |
+
},
|
| 769 |
+
"layer_24": {
|
| 770 |
+
"intermediate_size": 11008,
|
| 771 |
+
"dead_count": 0,
|
| 772 |
+
"dead_fraction": 0.0,
|
| 773 |
+
"mean_activation_freq": 0.9816908261696844,
|
| 774 |
+
"min_activation_freq": 0.9274269928476973
|
| 775 |
+
},
|
| 776 |
+
"layer_25": {
|
| 777 |
+
"intermediate_size": 11008,
|
| 778 |
+
"dead_count": 0,
|
| 779 |
+
"dead_fraction": 0.0,
|
| 780 |
+
"mean_activation_freq": 0.9837514577072142,
|
| 781 |
+
"min_activation_freq": 0.9514984390356351
|
| 782 |
+
},
|
| 783 |
+
"layer_26": {
|
| 784 |
+
"intermediate_size": 11008,
|
| 785 |
+
"dead_count": 0,
|
| 786 |
+
"dead_fraction": 0.0,
|
| 787 |
+
"mean_activation_freq": 0.9857234276753851,
|
| 788 |
+
"min_activation_freq": 0.9555944987625067
|
| 789 |
+
},
|
| 790 |
+
"layer_27": {
|
| 791 |
+
"intermediate_size": 11008,
|
| 792 |
+
"dead_count": 0,
|
| 793 |
+
"dead_fraction": 0.0,
|
| 794 |
+
"mean_activation_freq": 0.9869553750483601,
|
| 795 |
+
"min_activation_freq": 0.9415442083202685
|
| 796 |
+
},
|
| 797 |
+
"layer_28": {
|
| 798 |
+
"intermediate_size": 11008,
|
| 799 |
+
"dead_count": 0,
|
| 800 |
+
"dead_fraction": 0.0,
|
| 801 |
+
"mean_activation_freq": 0.9873200982021422,
|
| 802 |
+
"min_activation_freq": 0.21353422409722472
|
| 803 |
+
},
|
| 804 |
+
"layer_29": {
|
| 805 |
+
"intermediate_size": 11008,
|
| 806 |
+
"dead_count": 0,
|
| 807 |
+
"dead_fraction": 0.0,
|
| 808 |
+
"mean_activation_freq": 0.9885330402274483,
|
| 809 |
+
"min_activation_freq": 0.9604604442086921
|
| 810 |
+
},
|
| 811 |
+
"layer_30": {
|
| 812 |
+
"intermediate_size": 11008,
|
| 813 |
+
"dead_count": 0,
|
| 814 |
+
"dead_fraction": 0.0,
|
| 815 |
+
"mean_activation_freq": 0.9900672389260549,
|
| 816 |
+
"min_activation_freq": 0.5442261669432489
|
| 817 |
+
},
|
| 818 |
+
"layer_31": {
|
| 819 |
+
"intermediate_size": 11008,
|
| 820 |
+
"dead_count": 0,
|
| 821 |
+
"dead_fraction": 0.0,
|
| 822 |
+
"mean_activation_freq": 0.9909378789977512,
|
| 823 |
+
"min_activation_freq": 0.9468776374968553
|
| 824 |
+
},
|
| 825 |
+
"layer_32": {
|
| 826 |
+
"intermediate_size": 11008,
|
| 827 |
+
"dead_count": 0,
|
| 828 |
+
"dead_fraction": 0.0,
|
| 829 |
+
"mean_activation_freq": 0.9891531399171736,
|
| 830 |
+
"min_activation_freq": 0.6514289113652335
|
| 831 |
+
},
|
| 832 |
+
"layer_33": {
|
| 833 |
+
"intermediate_size": 11008,
|
| 834 |
+
"dead_count": 0,
|
| 835 |
+
"dead_fraction": 0.0,
|
| 836 |
+
"mean_activation_freq": 0.987075201467183,
|
| 837 |
+
"min_activation_freq": 0.923854187709838
|
| 838 |
+
},
|
| 839 |
+
"layer_34": {
|
| 840 |
+
"intermediate_size": 11008,
|
| 841 |
+
"dead_count": 0,
|
| 842 |
+
"dead_fraction": 0.0,
|
| 843 |
+
"mean_activation_freq": 0.9882194013382384,
|
| 844 |
+
"min_activation_freq": 0.8849838822218615
|
| 845 |
+
},
|
| 846 |
+
"layer_35": {
|
| 847 |
+
"intermediate_size": 11008,
|
| 848 |
+
"dead_count": 0,
|
| 849 |
+
"dead_fraction": 0.0,
|
| 850 |
+
"mean_activation_freq": 0.9918543054176937,
|
| 851 |
+
"min_activation_freq": 0.00743115707180684
|
| 852 |
+
},
|
| 853 |
+
"_overall": {
|
| 854 |
+
"dead_count": 11330,
|
| 855 |
+
"intermediate_total": 396288,
|
| 856 |
+
"dead_fraction": 0.02859031815245478
|
| 857 |
+
}
|
| 858 |
+
},
|
| 859 |
+
"size": 11182,
|
| 860 |
+
"size_pre_filter": 11182,
|
| 861 |
+
"skipped_long": 0
|
| 862 |
+
},
|
| 863 |
+
"negative": {
|
| 864 |
+
"loss": 1.2941068873798702,
|
| 865 |
+
"token_entropy": 0.047440475201673875,
|
| 866 |
+
"num_supervised_tokens": 8046154,
|
| 867 |
+
"kl_from_init": 3.010003556061493,
|
| 868 |
+
"kl_to_init": 0.4011514692235804,
|
| 869 |
+
"dead_units": {
|
| 870 |
+
"layer_0": {
|
| 871 |
+
"intermediate_size": 11008,
|
| 872 |
+
"dead_count": 0,
|
| 873 |
+
"dead_fraction": 0.0,
|
| 874 |
+
"mean_activation_freq": 0.9239432561895409,
|
| 875 |
+
"min_activation_freq": 0.784582547139913
|
| 876 |
+
},
|
| 877 |
+
"layer_1": {
|
| 878 |
+
"intermediate_size": 11008,
|
| 879 |
+
"dead_count": 1047,
|
| 880 |
+
"dead_fraction": 0.0951126453488372,
|
| 881 |
+
"mean_activation_freq": 0.14731663420578273,
|
| 882 |
+
"min_activation_freq": 0.0
|
| 883 |
+
},
|
| 884 |
+
"layer_2": {
|
| 885 |
+
"intermediate_size": 11008,
|
| 886 |
+
"dead_count": 629,
|
| 887 |
+
"dead_fraction": 0.057140261627906974,
|
| 888 |
+
"mean_activation_freq": 0.1664765267957849,
|
| 889 |
+
"min_activation_freq": 0.0
|
| 890 |
+
},
|
| 891 |
+
"layer_3": {
|
| 892 |
+
"intermediate_size": 11008,
|
| 893 |
+
"dead_count": 0,
|
| 894 |
+
"dead_fraction": 0.0,
|
| 895 |
+
"mean_activation_freq": 0.3878682846307256,
|
| 896 |
+
"min_activation_freq": 8.699808629066757e-07
|
| 897 |
+
},
|
| 898 |
+
"layer_4": {
|
| 899 |
+
"intermediate_size": 11008,
|
| 900 |
+
"dead_count": 0,
|
| 901 |
+
"dead_fraction": 0.0,
|
| 902 |
+
"mean_activation_freq": 0.5542583252623581,
|
| 903 |
+
"min_activation_freq": 7.208412864083885e-06
|
| 904 |
+
},
|
| 905 |
+
"layer_5": {
|
| 906 |
+
"intermediate_size": 11008,
|
| 907 |
+
"dead_count": 0,
|
| 908 |
+
"dead_fraction": 0.0,
|
| 909 |
+
"mean_activation_freq": 0.7155630760682334,
|
| 910 |
+
"min_activation_freq": 2.3613766278895482e-05
|
| 911 |
+
},
|
| 912 |
+
"layer_6": {
|
| 913 |
+
"intermediate_size": 11008,
|
| 914 |
+
"dead_count": 0,
|
| 915 |
+
"dead_fraction": 0.0,
|
| 916 |
+
"mean_activation_freq": 0.8693184657595491,
|
| 917 |
+
"min_activation_freq": 0.08818809582814348
|
| 918 |
+
},
|
| 919 |
+
"layer_7": {
|
| 920 |
+
"intermediate_size": 11008,
|
| 921 |
+
"dead_count": 0,
|
| 922 |
+
"dead_fraction": 0.0,
|
| 923 |
+
"mean_activation_freq": 0.8859820361353913,
|
| 924 |
+
"min_activation_freq": 0.03549024788737576
|
| 925 |
+
},
|
| 926 |
+
"layer_8": {
|
| 927 |
+
"intermediate_size": 11008,
|
| 928 |
+
"dead_count": 0,
|
| 929 |
+
"dead_fraction": 0.0,
|
| 930 |
+
"mean_activation_freq": 0.9409312061378086,
|
| 931 |
+
"min_activation_freq": 0.09162501736854652
|
| 932 |
+
},
|
| 933 |
+
"layer_9": {
|
| 934 |
+
"intermediate_size": 11008,
|
| 935 |
+
"dead_count": 0,
|
| 936 |
+
"dead_fraction": 0.0,
|
| 937 |
+
"mean_activation_freq": 0.9491183133648421,
|
| 938 |
+
"min_activation_freq": 0.26968412486263627
|
| 939 |
+
},
|
| 940 |
+
"layer_10": {
|
| 941 |
+
"intermediate_size": 11008,
|
| 942 |
+
"dead_count": 0,
|
| 943 |
+
"dead_fraction": 0.0,
|
| 944 |
+
"mean_activation_freq": 0.9733824551899086,
|
| 945 |
+
"min_activation_freq": 0.6732606659032377
|
| 946 |
+
},
|
| 947 |
+
"layer_11": {
|
| 948 |
+
"intermediate_size": 11008,
|
| 949 |
+
"dead_count": 0,
|
| 950 |
+
"dead_fraction": 0.0,
|
| 951 |
+
"mean_activation_freq": 0.9850688562652539,
|
| 952 |
+
"min_activation_freq": 0.9320812154477779
|
| 953 |
+
},
|
| 954 |
+
"layer_12": {
|
| 955 |
+
"intermediate_size": 11008,
|
| 956 |
+
"dead_count": 0,
|
| 957 |
+
"dead_fraction": 0.0,
|
| 958 |
+
"mean_activation_freq": 0.9867423640801477,
|
| 959 |
+
"min_activation_freq": 0.9199040933096732
|
| 960 |
+
},
|
| 961 |
+
"layer_13": {
|
| 962 |
+
"intermediate_size": 11008,
|
| 963 |
+
"dead_count": 0,
|
| 964 |
+
"dead_fraction": 0.0,
|
| 965 |
+
"mean_activation_freq": 0.980559855058475,
|
| 966 |
+
"min_activation_freq": 0.9006960344035175
|
| 967 |
+
},
|
| 968 |
+
"layer_14": {
|
| 969 |
+
"intermediate_size": 11008,
|
| 970 |
+
"dead_count": 0,
|
| 971 |
+
"dead_fraction": 0.0,
|
| 972 |
+
"mean_activation_freq": 0.9828507287673612,
|
| 973 |
+
"min_activation_freq": 0.896837544993546
|
| 974 |
+
},
|
| 975 |
+
"layer_15": {
|
| 976 |
+
"intermediate_size": 11008,
|
| 977 |
+
"dead_count": 0,
|
| 978 |
+
"dead_fraction": 0.0,
|
| 979 |
+
"mean_activation_freq": 0.9801063620999245,
|
| 980 |
+
"min_activation_freq": 0.910654332492269
|
| 981 |
+
},
|
| 982 |
+
"layer_16": {
|
| 983 |
+
"intermediate_size": 11008,
|
| 984 |
+
"dead_count": 0,
|
| 985 |
+
"dead_fraction": 0.0,
|
| 986 |
+
"mean_activation_freq": 0.9795157329998326,
|
| 987 |
+
"min_activation_freq": 0.907307516112667
|
| 988 |
+
},
|
| 989 |
+
"layer_17": {
|
| 990 |
+
"intermediate_size": 11008,
|
| 991 |
+
"dead_count": 0,
|
| 992 |
+
"dead_fraction": 0.0,
|
| 993 |
+
"mean_activation_freq": 0.9794251678181344,
|
| 994 |
+
"min_activation_freq": 0.9215938447113988
|
| 995 |
+
},
|
| 996 |
+
"layer_18": {
|
| 997 |
+
"intermediate_size": 11008,
|
| 998 |
+
"dead_count": 0,
|
| 999 |
+
"dead_fraction": 0.0,
|
| 1000 |
+
"mean_activation_freq": 0.9798689370447474,
|
| 1001 |
+
"min_activation_freq": 0.9246137968525087
|
| 1002 |
+
},
|
| 1003 |
+
"layer_19": {
|
| 1004 |
+
"intermediate_size": 11008,
|
| 1005 |
+
"dead_count": 0,
|
| 1006 |
+
"dead_fraction": 0.0,
|
| 1007 |
+
"mean_activation_freq": 0.9768583832846803,
|
| 1008 |
+
"min_activation_freq": 0.918726263504278
|
| 1009 |
+
},
|
| 1010 |
+
"layer_20": {
|
| 1011 |
+
"intermediate_size": 11008,
|
| 1012 |
+
"dead_count": 0,
|
| 1013 |
+
"dead_fraction": 0.0,
|
| 1014 |
+
"mean_activation_freq": 0.979419765979422,
|
| 1015 |
+
"min_activation_freq": 0.9150821622355227
|
| 1016 |
+
},
|
| 1017 |
+
"layer_21": {
|
| 1018 |
+
"intermediate_size": 11008,
|
| 1019 |
+
"dead_count": 0,
|
| 1020 |
+
"dead_fraction": 0.0,
|
| 1021 |
+
"mean_activation_freq": 0.9794817386579359,
|
| 1022 |
+
"min_activation_freq": 0.9222196095177895
|
| 1023 |
+
},
|
| 1024 |
+
"layer_22": {
|
| 1025 |
+
"intermediate_size": 11008,
|
| 1026 |
+
"dead_count": 0,
|
| 1027 |
+
"dead_fraction": 0.0,
|
| 1028 |
+
"mean_activation_freq": 0.9792024632623161,
|
| 1029 |
+
"min_activation_freq": 0.9303806514267562
|
| 1030 |
+
},
|
| 1031 |
+
"layer_23": {
|
| 1032 |
+
"intermediate_size": 11008,
|
| 1033 |
+
"dead_count": 0,
|
| 1034 |
+
"dead_fraction": 0.0,
|
| 1035 |
+
"mean_activation_freq": 0.9792918350090174,
|
| 1036 |
+
"min_activation_freq": 0.9388960241128868
|
| 1037 |
+
},
|
| 1038 |
+
"layer_24": {
|
| 1039 |
+
"intermediate_size": 11008,
|
| 1040 |
+
"dead_count": 0,
|
| 1041 |
+
"dead_fraction": 0.0,
|
| 1042 |
+
"mean_activation_freq": 0.9814430858216004,
|
| 1043 |
+
"min_activation_freq": 0.9295756705626067
|
| 1044 |
+
},
|
| 1045 |
+
"layer_25": {
|
| 1046 |
+
"intermediate_size": 11008,
|
| 1047 |
+
"dead_count": 0,
|
| 1048 |
+
"dead_fraction": 0.0,
|
| 1049 |
+
"mean_activation_freq": 0.9834818708223181,
|
| 1050 |
+
"min_activation_freq": 0.9523122475657314
|
| 1051 |
+
},
|
| 1052 |
+
"layer_26": {
|
| 1053 |
+
"intermediate_size": 11008,
|
| 1054 |
+
"dead_count": 0,
|
| 1055 |
+
"dead_fraction": 0.0,
|
| 1056 |
+
"mean_activation_freq": 0.9855015297133097,
|
| 1057 |
+
"min_activation_freq": 0.9556205362214046
|
| 1058 |
+
},
|
| 1059 |
+
"layer_27": {
|
| 1060 |
+
"intermediate_size": 11008,
|
| 1061 |
+
"dead_count": 0,
|
| 1062 |
+
"dead_fraction": 0.0,
|
| 1063 |
+
"mean_activation_freq": 0.9867652590418997,
|
| 1064 |
+
"min_activation_freq": 0.9384826589200257
|
| 1065 |
+
},
|
| 1066 |
+
"layer_28": {
|
| 1067 |
+
"intermediate_size": 11008,
|
| 1068 |
+
"dead_count": 0,
|
| 1069 |
+
"dead_fraction": 0.0,
|
| 1070 |
+
"mean_activation_freq": 0.9871922585789992,
|
| 1071 |
+
"min_activation_freq": 0.21872673577960353
|
| 1072 |
+
},
|
| 1073 |
+
"layer_29": {
|
| 1074 |
+
"intermediate_size": 11008,
|
| 1075 |
+
"dead_count": 0,
|
| 1076 |
+
"dead_fraction": 0.0,
|
| 1077 |
+
"mean_activation_freq": 0.9884141922232059,
|
| 1078 |
+
"min_activation_freq": 0.9593906604323009
|
| 1079 |
+
},
|
| 1080 |
+
"layer_30": {
|
| 1081 |
+
"intermediate_size": 11008,
|
| 1082 |
+
"dead_count": 0,
|
| 1083 |
+
"dead_fraction": 0.0,
|
| 1084 |
+
"mean_activation_freq": 0.9899860308924185,
|
| 1085 |
+
"min_activation_freq": 0.5672097501489531
|
| 1086 |
+
},
|
| 1087 |
+
"layer_31": {
|
| 1088 |
+
"intermediate_size": 11008,
|
| 1089 |
+
"dead_count": 0,
|
| 1090 |
+
"dead_fraction": 0.0,
|
| 1091 |
+
"mean_activation_freq": 0.9909089696048867,
|
| 1092 |
+
"min_activation_freq": 0.947924312659191
|
| 1093 |
+
},
|
| 1094 |
+
"layer_32": {
|
| 1095 |
+
"intermediate_size": 11008,
|
| 1096 |
+
"dead_count": 0,
|
| 1097 |
+
"dead_fraction": 0.0,
|
| 1098 |
+
"mean_activation_freq": 0.9891414935939696,
|
| 1099 |
+
"min_activation_freq": 0.6747065740973887
|
| 1100 |
+
},
|
| 1101 |
+
"layer_33": {
|
| 1102 |
+
"intermediate_size": 11008,
|
| 1103 |
+
"dead_count": 0,
|
| 1104 |
+
"dead_fraction": 0.0,
|
| 1105 |
+
"mean_activation_freq": 0.9870862253597502,
|
| 1106 |
+
"min_activation_freq": 0.924674944078873
|
| 1107 |
+
},
|
| 1108 |
+
"layer_34": {
|
| 1109 |
+
"intermediate_size": 11008,
|
| 1110 |
+
"dead_count": 0,
|
| 1111 |
+
"dead_fraction": 0.0,
|
| 1112 |
+
"mean_activation_freq": 0.9881647040980156,
|
| 1113 |
+
"min_activation_freq": 0.894632267789058
|
| 1114 |
+
},
|
| 1115 |
+
"layer_35": {
|
| 1116 |
+
"intermediate_size": 11008,
|
| 1117 |
+
"dead_count": 0,
|
| 1118 |
+
"dead_fraction": 0.0,
|
| 1119 |
+
"mean_activation_freq": 0.9921612932039143,
|
| 1120 |
+
"min_activation_freq": 0.017718403102898603
|
| 1121 |
+
},
|
| 1122 |
+
"_overall": {
|
| 1123 |
+
"dead_count": 1676,
|
| 1124 |
+
"intermediate_total": 396288,
|
| 1125 |
+
"dead_fraction": 0.004229247416020672
|
| 1126 |
+
}
|
| 1127 |
+
},
|
| 1128 |
+
"size": 18514,
|
| 1129 |
+
"size_pre_filter": 18514,
|
| 1130 |
+
"skipped_long": 0
|
| 1131 |
+
}
|
| 1132 |
+
},
|
| 1133 |
+
"new_data": {
|
| 1134 |
+
"num_records": 0,
|
| 1135 |
+
"source_steps": [],
|
| 1136 |
+
"num_source_steps": 0,
|
| 1137 |
+
"num_positives_pre_cap": 0,
|
| 1138 |
+
"num_negatives_pre_cap": 0,
|
| 1139 |
+
"positive": {
|
| 1140 |
+
"size": 0
|
| 1141 |
+
},
|
| 1142 |
+
"negative": {
|
| 1143 |
+
"size": 0
|
| 1144 |
+
}
|
| 1145 |
+
}
|
| 1146 |
+
}
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_750/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"eos_token_id": 151643,
|
| 4 |
+
"max_new_tokens": 2048,
|
| 5 |
+
"transformers_version": "4.57.6"
|
| 6 |
+
}
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_750/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_750/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:514506c284456f854423a621efa2ebe7374cb51a2852d1670df0e18b2ff1a2f1
|
| 3 |
+
size 4969102704
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_750/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0edaf00bcfc35cc1c62e9817618af72644a95907e959038334471bb4964ca6ad
|
| 3 |
+
size 1825154320
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_750/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,443 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 3397103616,
|
| 4 |
+
"total_size": 6794207232
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 37 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 48 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 70 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 73 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 94 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 95 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 105 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 128 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 143 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 164 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 166 |
+
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 167 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 168 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 169 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 176 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 177 |
+
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 178 |
+
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 179 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 181 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 188 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 189 |
+
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 190 |
+
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 191 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 192 |
+
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 193 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 200 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 202 |
+
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 203 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 205 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 212 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 213 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 215 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 216 |
+
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 217 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 224 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 225 |
+
"model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 226 |
+
"model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 227 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 228 |
+
"model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 229 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 236 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 237 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 239 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 240 |
+
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 248 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 249 |
+
"model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 250 |
+
"model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 251 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 252 |
+
"model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 253 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 260 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 273 |
+
"model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 274 |
+
"model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 275 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 276 |
+
"model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 277 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 278 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 279 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 280 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 281 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 282 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 283 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 287 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 288 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 292 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 294 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 295 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 296 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 298 |
+
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 299 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 300 |
+
"model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 302 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 303 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 304 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 305 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 306 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 307 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 308 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 309 |
+
"model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 310 |
+
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 311 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 312 |
+
"model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 314 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 315 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 316 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 317 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 318 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 319 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 320 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 323 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 324 |
+
"model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 325 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 326 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 327 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 328 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 329 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 330 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 331 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 332 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 333 |
+
"model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 334 |
+
"model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 335 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 336 |
+
"model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 337 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 338 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 339 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 340 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 345 |
+
"model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 346 |
+
"model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 348 |
+
"model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 349 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 350 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 351 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 353 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 354 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 355 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 356 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 363 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 365 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 366 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 367 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 370 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 372 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 382 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 385 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 388 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 394 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 397 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 399 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 400 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 405 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 406 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 407 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 408 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 409 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 410 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 411 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 412 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 413 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 415 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 416 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 417 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 418 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 419 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 420 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 421 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 422 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 423 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 424 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 425 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 426 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 427 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 428 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 429 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 430 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 431 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 432 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 433 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 434 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 435 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 436 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 437 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 438 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 439 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 440 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 441 |
+
"model.norm.weight": "model-00001-of-00002.safetensors"
|
| 442 |
+
}
|
| 443 |
+
}
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_750/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_750/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_750/tokenizer_config.json
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"clean_up_tokenization_spaces": false,
|
| 199 |
+
"eos_token": "<|endoftext|>",
|
| 200 |
+
"errors": "replace",
|
| 201 |
+
"extra_special_tokens": {},
|
| 202 |
+
"model_max_length": 131072,
|
| 203 |
+
"pad_token": "<|endoftext|>",
|
| 204 |
+
"split_special_tokens": false,
|
| 205 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 206 |
+
"unk_token": null
|
| 207 |
+
}
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_750/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_800/added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_800/chat_template.jinja
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'You are a helpful assistant.' }}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 9 |
+
{%- for tool in tools %}
|
| 10 |
+
{{- "\n" }}
|
| 11 |
+
{{- tool | tojson }}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 14 |
+
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endif %}
|
| 21 |
+
{%- for message in messages %}
|
| 22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
+
{%- elif message.role == "assistant" %}
|
| 25 |
+
{{- '<|im_start|>' + message.role }}
|
| 26 |
+
{%- if message.content %}
|
| 27 |
+
{{- '\n' + message.content }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- for tool_call in message.tool_calls %}
|
| 30 |
+
{%- if tool_call.function is defined %}
|
| 31 |
+
{%- set tool_call = tool_call.function %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
+
{{- tool_call.name }}
|
| 35 |
+
{{- '", "arguments": ' }}
|
| 36 |
+
{{- tool_call.arguments | tojson }}
|
| 37 |
+
{{- '}\n</tool_call>' }}
|
| 38 |
+
{%- endfor %}
|
| 39 |
+
{{- '<|im_end|>\n' }}
|
| 40 |
+
{%- elif message.role == "tool" %}
|
| 41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
+
{{- '<|im_start|>user' }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{{- '\n<tool_response>\n' }}
|
| 45 |
+
{{- message.content }}
|
| 46 |
+
{{- '\n</tool_response>' }}
|
| 47 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
+
{{- '<|im_end|>\n' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{%- if add_generation_prompt %}
|
| 53 |
+
{{- '<|im_start|>assistant\n' }}
|
| 54 |
+
{%- endif %}
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_800/config.json
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"dtype": "bfloat16",
|
| 7 |
+
"eos_token_id": 151643,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 2048,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 11008,
|
| 12 |
+
"layer_types": [
|
| 13 |
+
"full_attention",
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention"
|
| 49 |
+
],
|
| 50 |
+
"max_position_embeddings": 32768,
|
| 51 |
+
"max_window_layers": 36,
|
| 52 |
+
"model_type": "qwen2",
|
| 53 |
+
"num_attention_heads": 16,
|
| 54 |
+
"num_hidden_layers": 36,
|
| 55 |
+
"num_key_value_heads": 2,
|
| 56 |
+
"pad_token_id": 151643,
|
| 57 |
+
"rms_norm_eps": 1e-06,
|
| 58 |
+
"rope_scaling": null,
|
| 59 |
+
"rope_theta": 1000000.0,
|
| 60 |
+
"sliding_window": null,
|
| 61 |
+
"tie_word_embeddings": true,
|
| 62 |
+
"transformers_version": "4.57.6",
|
| 63 |
+
"use_cache": true,
|
| 64 |
+
"use_mrope": false,
|
| 65 |
+
"use_sliding_window": false,
|
| 66 |
+
"vocab_size": 151936
|
| 67 |
+
}
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_800/eval_metrics.json
ADDED
|
@@ -0,0 +1,1148 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"global_step": 800,
|
| 3 |
+
"ckpt_dir": "/mnt/mystorageoutput/projects/jy_intern/amlt-results/7213899235.25497-028989ec-3fee/qwen3b_kk_rlrb_bs128_nobuf/checkpoints_hf_format/global_step_800",
|
| 4 |
+
"rollouts_dir": "/mnt/mystorageoutput/projects/jy_intern/amlt-results/7213899235.25497-028989ec-3fee/qwen3b_kk_rlrb_bs128_nobuf/rollouts/training",
|
| 5 |
+
"init_model_path": "Qwen/Qwen2.5-3B",
|
| 6 |
+
"prev_step": null,
|
| 7 |
+
"positive_score": 1.0,
|
| 8 |
+
"negative_score": 0.0,
|
| 9 |
+
"history_step_stride": 25,
|
| 10 |
+
"max_samples_per_class": 0,
|
| 11 |
+
"in_batch": {
|
| 12 |
+
"num_records": 1024,
|
| 13 |
+
"source_steps": [
|
| 14 |
+
800
|
| 15 |
+
],
|
| 16 |
+
"num_source_steps": 1,
|
| 17 |
+
"num_positives_pre_cap": 590,
|
| 18 |
+
"num_negatives_pre_cap": 434,
|
| 19 |
+
"positive": {
|
| 20 |
+
"loss": 0.22846651220594708,
|
| 21 |
+
"token_entropy": 0.02124891934445546,
|
| 22 |
+
"num_supervised_tokens": 213925,
|
| 23 |
+
"kl_from_init": 3.1852006455332624,
|
| 24 |
+
"kl_to_init": 0.381338181000273,
|
| 25 |
+
"dead_units": {
|
| 26 |
+
"layer_0": {
|
| 27 |
+
"intermediate_size": 11008,
|
| 28 |
+
"dead_count": 0,
|
| 29 |
+
"dead_fraction": 0.0,
|
| 30 |
+
"mean_activation_freq": 0.9239543733404719,
|
| 31 |
+
"min_activation_freq": 0.7831669977795956
|
| 32 |
+
},
|
| 33 |
+
"layer_1": {
|
| 34 |
+
"intermediate_size": 11008,
|
| 35 |
+
"dead_count": 8836,
|
| 36 |
+
"dead_fraction": 0.8026889534883721,
|
| 37 |
+
"mean_activation_freq": 0.14746906347584327,
|
| 38 |
+
"min_activation_freq": 0.0
|
| 39 |
+
},
|
| 40 |
+
"layer_2": {
|
| 41 |
+
"intermediate_size": 11008,
|
| 42 |
+
"dead_count": 7454,
|
| 43 |
+
"dead_fraction": 0.6771438953488372,
|
| 44 |
+
"mean_activation_freq": 0.1664085261182875,
|
| 45 |
+
"min_activation_freq": 0.0
|
| 46 |
+
},
|
| 47 |
+
"layer_3": {
|
| 48 |
+
"intermediate_size": 11008,
|
| 49 |
+
"dead_count": 423,
|
| 50 |
+
"dead_fraction": 0.0384265988372093,
|
| 51 |
+
"mean_activation_freq": 0.38351541543575096,
|
| 52 |
+
"min_activation_freq": 0.0
|
| 53 |
+
},
|
| 54 |
+
"layer_4": {
|
| 55 |
+
"intermediate_size": 11008,
|
| 56 |
+
"dead_count": 32,
|
| 57 |
+
"dead_fraction": 0.0029069767441860465,
|
| 58 |
+
"mean_activation_freq": 0.5462655884377268,
|
| 59 |
+
"min_activation_freq": 0.0
|
| 60 |
+
},
|
| 61 |
+
"layer_5": {
|
| 62 |
+
"intermediate_size": 11008,
|
| 63 |
+
"dead_count": 8,
|
| 64 |
+
"dead_fraction": 0.0007267441860465116,
|
| 65 |
+
"mean_activation_freq": 0.7138580867425282,
|
| 66 |
+
"min_activation_freq": 0.0
|
| 67 |
+
},
|
| 68 |
+
"layer_6": {
|
| 69 |
+
"intermediate_size": 11008,
|
| 70 |
+
"dead_count": 0,
|
| 71 |
+
"dead_fraction": 0.0,
|
| 72 |
+
"mean_activation_freq": 0.8697419845815068,
|
| 73 |
+
"min_activation_freq": 0.09221923571345098
|
| 74 |
+
},
|
| 75 |
+
"layer_7": {
|
| 76 |
+
"intermediate_size": 11008,
|
| 77 |
+
"dead_count": 0,
|
| 78 |
+
"dead_fraction": 0.0,
|
| 79 |
+
"mean_activation_freq": 0.8843827167204328,
|
| 80 |
+
"min_activation_freq": 0.04152389856258034
|
| 81 |
+
},
|
| 82 |
+
"layer_8": {
|
| 83 |
+
"intermediate_size": 11008,
|
| 84 |
+
"dead_count": 0,
|
| 85 |
+
"dead_fraction": 0.0,
|
| 86 |
+
"mean_activation_freq": 0.9411821491686393,
|
| 87 |
+
"min_activation_freq": 0.08347317985275213
|
| 88 |
+
},
|
| 89 |
+
"layer_9": {
|
| 90 |
+
"intermediate_size": 11008,
|
| 91 |
+
"dead_count": 0,
|
| 92 |
+
"dead_fraction": 0.0,
|
| 93 |
+
"mean_activation_freq": 0.949455535944324,
|
| 94 |
+
"min_activation_freq": 0.251485333644969
|
| 95 |
+
},
|
| 96 |
+
"layer_10": {
|
| 97 |
+
"intermediate_size": 11008,
|
| 98 |
+
"dead_count": 0,
|
| 99 |
+
"dead_fraction": 0.0,
|
| 100 |
+
"mean_activation_freq": 0.9740596862761618,
|
| 101 |
+
"min_activation_freq": 0.6816734836975575
|
| 102 |
+
},
|
| 103 |
+
"layer_11": {
|
| 104 |
+
"intermediate_size": 11008,
|
| 105 |
+
"dead_count": 0,
|
| 106 |
+
"dead_fraction": 0.0,
|
| 107 |
+
"mean_activation_freq": 0.9851513385104266,
|
| 108 |
+
"min_activation_freq": 0.9376370223209068
|
| 109 |
+
},
|
| 110 |
+
"layer_12": {
|
| 111 |
+
"intermediate_size": 11008,
|
| 112 |
+
"dead_count": 0,
|
| 113 |
+
"dead_fraction": 0.0,
|
| 114 |
+
"mean_activation_freq": 0.9868049346244471,
|
| 115 |
+
"min_activation_freq": 0.9187238518172256
|
| 116 |
+
},
|
| 117 |
+
"layer_13": {
|
| 118 |
+
"intermediate_size": 11008,
|
| 119 |
+
"dead_count": 0,
|
| 120 |
+
"dead_fraction": 0.0,
|
| 121 |
+
"mean_activation_freq": 0.9807176214529923,
|
| 122 |
+
"min_activation_freq": 0.9038120836741849
|
| 123 |
+
},
|
| 124 |
+
"layer_14": {
|
| 125 |
+
"intermediate_size": 11008,
|
| 126 |
+
"dead_count": 0,
|
| 127 |
+
"dead_fraction": 0.0,
|
| 128 |
+
"mean_activation_freq": 0.9830469019652073,
|
| 129 |
+
"min_activation_freq": 0.887418487787776
|
| 130 |
+
},
|
| 131 |
+
"layer_15": {
|
| 132 |
+
"intermediate_size": 11008,
|
| 133 |
+
"dead_count": 0,
|
| 134 |
+
"dead_fraction": 0.0,
|
| 135 |
+
"mean_activation_freq": 0.9803359979487759,
|
| 136 |
+
"min_activation_freq": 0.9080705854855673
|
| 137 |
+
},
|
| 138 |
+
"layer_16": {
|
| 139 |
+
"intermediate_size": 11008,
|
| 140 |
+
"dead_count": 0,
|
| 141 |
+
"dead_fraction": 0.0,
|
| 142 |
+
"mean_activation_freq": 0.9798200677535867,
|
| 143 |
+
"min_activation_freq": 0.9004931634918779
|
| 144 |
+
},
|
| 145 |
+
"layer_17": {
|
| 146 |
+
"intermediate_size": 11008,
|
| 147 |
+
"dead_count": 0,
|
| 148 |
+
"dead_fraction": 0.0,
|
| 149 |
+
"mean_activation_freq": 0.9799694889740753,
|
| 150 |
+
"min_activation_freq": 0.9170924389388804
|
| 151 |
+
},
|
| 152 |
+
"layer_18": {
|
| 153 |
+
"intermediate_size": 11008,
|
| 154 |
+
"dead_count": 0,
|
| 155 |
+
"dead_fraction": 0.0,
|
| 156 |
+
"mean_activation_freq": 0.9805474599539069,
|
| 157 |
+
"min_activation_freq": 0.9199859763935958
|
| 158 |
+
},
|
| 159 |
+
"layer_19": {
|
| 160 |
+
"intermediate_size": 11008,
|
| 161 |
+
"dead_count": 0,
|
| 162 |
+
"dead_fraction": 0.0,
|
| 163 |
+
"mean_activation_freq": 0.9775518097178701,
|
| 164 |
+
"min_activation_freq": 0.9201869814187215
|
| 165 |
+
},
|
| 166 |
+
"layer_20": {
|
| 167 |
+
"intermediate_size": 11008,
|
| 168 |
+
"dead_count": 0,
|
| 169 |
+
"dead_fraction": 0.0,
|
| 170 |
+
"mean_activation_freq": 0.9800574265493232,
|
| 171 |
+
"min_activation_freq": 0.9125020451092672
|
| 172 |
+
},
|
| 173 |
+
"layer_21": {
|
| 174 |
+
"intermediate_size": 11008,
|
| 175 |
+
"dead_count": 0,
|
| 176 |
+
"dead_fraction": 0.0,
|
| 177 |
+
"mean_activation_freq": 0.9799338660242805,
|
| 178 |
+
"min_activation_freq": 0.9199111838261073
|
| 179 |
+
},
|
| 180 |
+
"layer_22": {
|
| 181 |
+
"intermediate_size": 11008,
|
| 182 |
+
"dead_count": 0,
|
| 183 |
+
"dead_fraction": 0.0,
|
| 184 |
+
"mean_activation_freq": 0.9796100334181724,
|
| 185 |
+
"min_activation_freq": 0.9252027579759261
|
| 186 |
+
},
|
| 187 |
+
"layer_23": {
|
| 188 |
+
"intermediate_size": 11008,
|
| 189 |
+
"dead_count": 0,
|
| 190 |
+
"dead_fraction": 0.0,
|
| 191 |
+
"mean_activation_freq": 0.9796073602531316,
|
| 192 |
+
"min_activation_freq": 0.9406333995559191
|
| 193 |
+
},
|
| 194 |
+
"layer_24": {
|
| 195 |
+
"intermediate_size": 11008,
|
| 196 |
+
"dead_count": 0,
|
| 197 |
+
"dead_fraction": 0.0,
|
| 198 |
+
"mean_activation_freq": 0.9816434992363113,
|
| 199 |
+
"min_activation_freq": 0.9302746289587471
|
| 200 |
+
},
|
| 201 |
+
"layer_25": {
|
| 202 |
+
"intermediate_size": 11008,
|
| 203 |
+
"dead_count": 0,
|
| 204 |
+
"dead_fraction": 0.0,
|
| 205 |
+
"mean_activation_freq": 0.9837073716167368,
|
| 206 |
+
"min_activation_freq": 0.9493560827392777
|
| 207 |
+
},
|
| 208 |
+
"layer_26": {
|
| 209 |
+
"intermediate_size": 11008,
|
| 210 |
+
"dead_count": 0,
|
| 211 |
+
"dead_fraction": 0.0,
|
| 212 |
+
"mean_activation_freq": 0.9856727084584632,
|
| 213 |
+
"min_activation_freq": 0.9534836975575551
|
| 214 |
+
},
|
| 215 |
+
"layer_27": {
|
| 216 |
+
"intermediate_size": 11008,
|
| 217 |
+
"dead_count": 0,
|
| 218 |
+
"dead_fraction": 0.0,
|
| 219 |
+
"mean_activation_freq": 0.9869145275967451,
|
| 220 |
+
"min_activation_freq": 0.9421853453313076
|
| 221 |
+
},
|
| 222 |
+
"layer_28": {
|
| 223 |
+
"intermediate_size": 11008,
|
| 224 |
+
"dead_count": 0,
|
| 225 |
+
"dead_fraction": 0.0,
|
| 226 |
+
"mean_activation_freq": 0.9872723253232089,
|
| 227 |
+
"min_activation_freq": 0.22585018113824937
|
| 228 |
+
},
|
| 229 |
+
"layer_29": {
|
| 230 |
+
"intermediate_size": 11008,
|
| 231 |
+
"dead_count": 0,
|
| 232 |
+
"dead_fraction": 0.0,
|
| 233 |
+
"mean_activation_freq": 0.9884746767402454,
|
| 234 |
+
"min_activation_freq": 0.9602664485216781
|
| 235 |
+
},
|
| 236 |
+
"layer_30": {
|
| 237 |
+
"intermediate_size": 11008,
|
| 238 |
+
"dead_count": 0,
|
| 239 |
+
"dead_fraction": 0.0,
|
| 240 |
+
"mean_activation_freq": 0.9900258042171375,
|
| 241 |
+
"min_activation_freq": 0.5667547037513146
|
| 242 |
+
},
|
| 243 |
+
"layer_31": {
|
| 244 |
+
"intermediate_size": 11008,
|
| 245 |
+
"dead_count": 0,
|
| 246 |
+
"dead_fraction": 0.0,
|
| 247 |
+
"mean_activation_freq": 0.9908556939307135,
|
| 248 |
+
"min_activation_freq": 0.9450975809278952
|
| 249 |
+
},
|
| 250 |
+
"layer_32": {
|
| 251 |
+
"intermediate_size": 11008,
|
| 252 |
+
"dead_count": 0,
|
| 253 |
+
"dead_fraction": 0.0,
|
| 254 |
+
"mean_activation_freq": 0.9890381030694304,
|
| 255 |
+
"min_activation_freq": 0.5024003739628374
|
| 256 |
+
},
|
| 257 |
+
"layer_33": {
|
| 258 |
+
"intermediate_size": 11008,
|
| 259 |
+
"dead_count": 0,
|
| 260 |
+
"dead_fraction": 0.0,
|
| 261 |
+
"mean_activation_freq": 0.986953785966066,
|
| 262 |
+
"min_activation_freq": 0.9277363561996026
|
| 263 |
+
},
|
| 264 |
+
"layer_34": {
|
| 265 |
+
"intermediate_size": 11008,
|
| 266 |
+
"dead_count": 0,
|
| 267 |
+
"dead_fraction": 0.0,
|
| 268 |
+
"mean_activation_freq": 0.9881610340099631,
|
| 269 |
+
"min_activation_freq": 0.8843847142690194
|
| 270 |
+
},
|
| 271 |
+
"layer_35": {
|
| 272 |
+
"intermediate_size": 11008,
|
| 273 |
+
"dead_count": 0,
|
| 274 |
+
"dead_fraction": 0.0,
|
| 275 |
+
"mean_activation_freq": 0.9917719648811933,
|
| 276 |
+
"min_activation_freq": 0.006376066378403646
|
| 277 |
+
},
|
| 278 |
+
"_overall": {
|
| 279 |
+
"dead_count": 16753,
|
| 280 |
+
"intermediate_total": 396288,
|
| 281 |
+
"dead_fraction": 0.042274810239018086
|
| 282 |
+
}
|
| 283 |
+
},
|
| 284 |
+
"size": 590,
|
| 285 |
+
"size_pre_filter": 590,
|
| 286 |
+
"skipped_long": 0
|
| 287 |
+
},
|
| 288 |
+
"negative": {
|
| 289 |
+
"loss": 0.3168102655818925,
|
| 290 |
+
"token_entropy": 0.02307344691011331,
|
| 291 |
+
"num_supervised_tokens": 188301,
|
| 292 |
+
"kl_from_init": 3.0714095322283206,
|
| 293 |
+
"kl_to_init": 0.3561845064161942,
|
| 294 |
+
"dead_units": {
|
| 295 |
+
"layer_0": {
|
| 296 |
+
"intermediate_size": 11008,
|
| 297 |
+
"dead_count": 0,
|
| 298 |
+
"dead_fraction": 0.0,
|
| 299 |
+
"mean_activation_freq": 0.9242351162268897,
|
| 300 |
+
"min_activation_freq": 0.7843187237454926
|
| 301 |
+
},
|
| 302 |
+
"layer_1": {
|
| 303 |
+
"intermediate_size": 11008,
|
| 304 |
+
"dead_count": 8842,
|
| 305 |
+
"dead_fraction": 0.803234011627907,
|
| 306 |
+
"mean_activation_freq": 0.1472054527438627,
|
| 307 |
+
"min_activation_freq": 0.0
|
| 308 |
+
},
|
| 309 |
+
"layer_2": {
|
| 310 |
+
"intermediate_size": 11008,
|
| 311 |
+
"dead_count": 7502,
|
| 312 |
+
"dead_fraction": 0.6815043604651163,
|
| 313 |
+
"mean_activation_freq": 0.16628240947308753,
|
| 314 |
+
"min_activation_freq": 0.0
|
| 315 |
+
},
|
| 316 |
+
"layer_3": {
|
| 317 |
+
"intermediate_size": 11008,
|
| 318 |
+
"dead_count": 473,
|
| 319 |
+
"dead_fraction": 0.04296875,
|
| 320 |
+
"mean_activation_freq": 0.38328771117692195,
|
| 321 |
+
"min_activation_freq": 0.0
|
| 322 |
+
},
|
| 323 |
+
"layer_4": {
|
| 324 |
+
"intermediate_size": 11008,
|
| 325 |
+
"dead_count": 28,
|
| 326 |
+
"dead_fraction": 0.002543604651162791,
|
| 327 |
+
"mean_activation_freq": 0.5482346113141096,
|
| 328 |
+
"min_activation_freq": 0.0
|
| 329 |
+
},
|
| 330 |
+
"layer_5": {
|
| 331 |
+
"intermediate_size": 11008,
|
| 332 |
+
"dead_count": 16,
|
| 333 |
+
"dead_fraction": 0.0014534883720930232,
|
| 334 |
+
"mean_activation_freq": 0.7154141417747105,
|
| 335 |
+
"min_activation_freq": 0.0
|
| 336 |
+
},
|
| 337 |
+
"layer_6": {
|
| 338 |
+
"intermediate_size": 11008,
|
| 339 |
+
"dead_count": 0,
|
| 340 |
+
"dead_fraction": 0.0,
|
| 341 |
+
"mean_activation_freq": 0.8700104514946259,
|
| 342 |
+
"min_activation_freq": 0.09409934094880007
|
| 343 |
+
},
|
| 344 |
+
"layer_7": {
|
| 345 |
+
"intermediate_size": 11008,
|
| 346 |
+
"dead_count": 0,
|
| 347 |
+
"dead_fraction": 0.0,
|
| 348 |
+
"mean_activation_freq": 0.8847211543680745,
|
| 349 |
+
"min_activation_freq": 0.04473688403141778
|
| 350 |
+
},
|
| 351 |
+
"layer_8": {
|
| 352 |
+
"intermediate_size": 11008,
|
| 353 |
+
"dead_count": 0,
|
| 354 |
+
"dead_fraction": 0.0,
|
| 355 |
+
"mean_activation_freq": 0.9411543701199947,
|
| 356 |
+
"min_activation_freq": 0.08446582864668802
|
| 357 |
+
},
|
| 358 |
+
"layer_9": {
|
| 359 |
+
"intermediate_size": 11008,
|
| 360 |
+
"dead_count": 0,
|
| 361 |
+
"dead_fraction": 0.0,
|
| 362 |
+
"mean_activation_freq": 0.9497242306062301,
|
| 363 |
+
"min_activation_freq": 0.26331246249356083
|
| 364 |
+
},
|
| 365 |
+
"layer_10": {
|
| 366 |
+
"intermediate_size": 11008,
|
| 367 |
+
"dead_count": 0,
|
| 368 |
+
"dead_fraction": 0.0,
|
| 369 |
+
"mean_activation_freq": 0.9741571405212747,
|
| 370 |
+
"min_activation_freq": 0.6915098698360604
|
| 371 |
+
},
|
| 372 |
+
"layer_11": {
|
| 373 |
+
"intermediate_size": 11008,
|
| 374 |
+
"dead_count": 0,
|
| 375 |
+
"dead_fraction": 0.0,
|
| 376 |
+
"mean_activation_freq": 0.9851283456608254,
|
| 377 |
+
"min_activation_freq": 0.9332133127280259
|
| 378 |
+
},
|
| 379 |
+
"layer_12": {
|
| 380 |
+
"intermediate_size": 11008,
|
| 381 |
+
"dead_count": 0,
|
| 382 |
+
"dead_fraction": 0.0,
|
| 383 |
+
"mean_activation_freq": 0.9867881411578729,
|
| 384 |
+
"min_activation_freq": 0.9188267720298884
|
| 385 |
+
},
|
| 386 |
+
"layer_13": {
|
| 387 |
+
"intermediate_size": 11008,
|
| 388 |
+
"dead_count": 0,
|
| 389 |
+
"dead_fraction": 0.0,
|
| 390 |
+
"mean_activation_freq": 0.9805610480477016,
|
| 391 |
+
"min_activation_freq": 0.9031178804148677
|
| 392 |
+
},
|
| 393 |
+
"layer_14": {
|
| 394 |
+
"intermediate_size": 11008,
|
| 395 |
+
"dead_count": 0,
|
| 396 |
+
"dead_fraction": 0.0,
|
| 397 |
+
"mean_activation_freq": 0.9829540668350081,
|
| 398 |
+
"min_activation_freq": 0.8891933659407014
|
| 399 |
+
},
|
| 400 |
+
"layer_15": {
|
| 401 |
+
"intermediate_size": 11008,
|
| 402 |
+
"dead_count": 0,
|
| 403 |
+
"dead_fraction": 0.0,
|
| 404 |
+
"mean_activation_freq": 0.9802479587242061,
|
| 405 |
+
"min_activation_freq": 0.9100535844206882
|
| 406 |
+
},
|
| 407 |
+
"layer_16": {
|
| 408 |
+
"intermediate_size": 11008,
|
| 409 |
+
"dead_count": 0,
|
| 410 |
+
"dead_fraction": 0.0,
|
| 411 |
+
"mean_activation_freq": 0.9797743169088631,
|
| 412 |
+
"min_activation_freq": 0.9010467283763761
|
| 413 |
+
},
|
| 414 |
+
"layer_17": {
|
| 415 |
+
"intermediate_size": 11008,
|
| 416 |
+
"dead_count": 0,
|
| 417 |
+
"dead_fraction": 0.0,
|
| 418 |
+
"mean_activation_freq": 0.9799637166111642,
|
| 419 |
+
"min_activation_freq": 0.9162033127811324
|
| 420 |
+
},
|
| 421 |
+
"layer_18": {
|
| 422 |
+
"intermediate_size": 11008,
|
| 423 |
+
"dead_count": 0,
|
| 424 |
+
"dead_fraction": 0.0,
|
| 425 |
+
"mean_activation_freq": 0.9805810435378205,
|
| 426 |
+
"min_activation_freq": 0.9217476274687867
|
| 427 |
+
},
|
| 428 |
+
"layer_19": {
|
| 429 |
+
"intermediate_size": 11008,
|
| 430 |
+
"dead_count": 0,
|
| 431 |
+
"dead_fraction": 0.0,
|
| 432 |
+
"mean_activation_freq": 0.9775503337532758,
|
| 433 |
+
"min_activation_freq": 0.9195437092739815
|
| 434 |
+
},
|
| 435 |
+
"layer_20": {
|
| 436 |
+
"intermediate_size": 11008,
|
| 437 |
+
"dead_count": 0,
|
| 438 |
+
"dead_fraction": 0.0,
|
| 439 |
+
"mean_activation_freq": 0.9800634378886884,
|
| 440 |
+
"min_activation_freq": 0.9164847770325172
|
| 441 |
+
},
|
| 442 |
+
"layer_21": {
|
| 443 |
+
"intermediate_size": 11008,
|
| 444 |
+
"dead_count": 0,
|
| 445 |
+
"dead_fraction": 0.0,
|
| 446 |
+
"mean_activation_freq": 0.9798355027130302,
|
| 447 |
+
"min_activation_freq": 0.9192197598525765
|
| 448 |
+
},
|
| 449 |
+
"layer_22": {
|
| 450 |
+
"intermediate_size": 11008,
|
| 451 |
+
"dead_count": 0,
|
| 452 |
+
"dead_fraction": 0.0,
|
| 453 |
+
"mean_activation_freq": 0.979449169118518,
|
| 454 |
+
"min_activation_freq": 0.9272016611701478
|
| 455 |
+
},
|
| 456 |
+
"layer_23": {
|
| 457 |
+
"intermediate_size": 11008,
|
| 458 |
+
"dead_count": 0,
|
| 459 |
+
"dead_fraction": 0.0,
|
| 460 |
+
"mean_activation_freq": 0.979364890108063,
|
| 461 |
+
"min_activation_freq": 0.939607330816087
|
| 462 |
+
},
|
| 463 |
+
"layer_24": {
|
| 464 |
+
"intermediate_size": 11008,
|
| 465 |
+
"dead_count": 0,
|
| 466 |
+
"dead_fraction": 0.0,
|
| 467 |
+
"mean_activation_freq": 0.9815107925801442,
|
| 468 |
+
"min_activation_freq": 0.9298038778338936
|
| 469 |
+
},
|
| 470 |
+
"layer_25": {
|
| 471 |
+
"intermediate_size": 11008,
|
| 472 |
+
"dead_count": 0,
|
| 473 |
+
"dead_fraction": 0.0,
|
| 474 |
+
"mean_activation_freq": 0.983528936090448,
|
| 475 |
+
"min_activation_freq": 0.9507118921301534
|
| 476 |
+
},
|
| 477 |
+
"layer_26": {
|
| 478 |
+
"intermediate_size": 11008,
|
| 479 |
+
"dead_count": 0,
|
| 480 |
+
"dead_fraction": 0.0,
|
| 481 |
+
"mean_activation_freq": 0.9855176587748921,
|
| 482 |
+
"min_activation_freq": 0.9551887669210467
|
| 483 |
+
},
|
| 484 |
+
"layer_27": {
|
| 485 |
+
"intermediate_size": 11008,
|
| 486 |
+
"dead_count": 0,
|
| 487 |
+
"dead_fraction": 0.0,
|
| 488 |
+
"mean_activation_freq": 0.9867770658938813,
|
| 489 |
+
"min_activation_freq": 0.9402552296588973
|
| 490 |
+
},
|
| 491 |
+
"layer_28": {
|
| 492 |
+
"intermediate_size": 11008,
|
| 493 |
+
"dead_count": 0,
|
| 494 |
+
"dead_fraction": 0.0,
|
| 495 |
+
"mean_activation_freq": 0.9871967584324727,
|
| 496 |
+
"min_activation_freq": 0.2392977201395638
|
| 497 |
+
},
|
| 498 |
+
"layer_29": {
|
| 499 |
+
"intermediate_size": 11008,
|
| 500 |
+
"dead_count": 0,
|
| 501 |
+
"dead_fraction": 0.0,
|
| 502 |
+
"mean_activation_freq": 0.9884074154784405,
|
| 503 |
+
"min_activation_freq": 0.958608823107684
|
| 504 |
+
},
|
| 505 |
+
"layer_30": {
|
| 506 |
+
"intermediate_size": 11008,
|
| 507 |
+
"dead_count": 0,
|
| 508 |
+
"dead_fraction": 0.0,
|
| 509 |
+
"mean_activation_freq": 0.9899759573999101,
|
| 510 |
+
"min_activation_freq": 0.5797685620363142
|
| 511 |
+
},
|
| 512 |
+
"layer_31": {
|
| 513 |
+
"intermediate_size": 11008,
|
| 514 |
+
"dead_count": 0,
|
| 515 |
+
"dead_fraction": 0.0,
|
| 516 |
+
"mean_activation_freq": 0.9908266314598607,
|
| 517 |
+
"min_activation_freq": 0.9442700782258193
|
| 518 |
+
},
|
| 519 |
+
"layer_32": {
|
| 520 |
+
"intermediate_size": 11008,
|
| 521 |
+
"dead_count": 0,
|
| 522 |
+
"dead_fraction": 0.0,
|
| 523 |
+
"mean_activation_freq": 0.9889978220406763,
|
| 524 |
+
"min_activation_freq": 0.4871986872082464
|
| 525 |
+
},
|
| 526 |
+
"layer_33": {
|
| 527 |
+
"intermediate_size": 11008,
|
| 528 |
+
"dead_count": 0,
|
| 529 |
+
"dead_fraction": 0.0,
|
| 530 |
+
"mean_activation_freq": 0.9868923929839941,
|
| 531 |
+
"min_activation_freq": 0.9288585828009411
|
| 532 |
+
},
|
| 533 |
+
"layer_34": {
|
| 534 |
+
"intermediate_size": 11008,
|
| 535 |
+
"dead_count": 0,
|
| 536 |
+
"dead_fraction": 0.0,
|
| 537 |
+
"mean_activation_freq": 0.9880888336306369,
|
| 538 |
+
"min_activation_freq": 0.8942331692343641
|
| 539 |
+
},
|
| 540 |
+
"layer_35": {
|
| 541 |
+
"intermediate_size": 11008,
|
| 542 |
+
"dead_count": 0,
|
| 543 |
+
"dead_fraction": 0.0,
|
| 544 |
+
"mean_activation_freq": 0.9919673108032872,
|
| 545 |
+
"min_activation_freq": 0.005916059925332314
|
| 546 |
+
},
|
| 547 |
+
"_overall": {
|
| 548 |
+
"dead_count": 16861,
|
| 549 |
+
"intermediate_total": 396288,
|
| 550 |
+
"dead_fraction": 0.04254733930878553
|
| 551 |
+
}
|
| 552 |
+
},
|
| 553 |
+
"size": 434,
|
| 554 |
+
"size_pre_filter": 434,
|
| 555 |
+
"skipped_long": 0
|
| 556 |
+
}
|
| 557 |
+
},
|
| 558 |
+
"old_data": {
|
| 559 |
+
"num_records": 31744,
|
| 560 |
+
"source_steps": [
|
| 561 |
+
25,
|
| 562 |
+
50,
|
| 563 |
+
75,
|
| 564 |
+
100,
|
| 565 |
+
125,
|
| 566 |
+
150,
|
| 567 |
+
175,
|
| 568 |
+
200,
|
| 569 |
+
225,
|
| 570 |
+
250,
|
| 571 |
+
275,
|
| 572 |
+
300,
|
| 573 |
+
325,
|
| 574 |
+
350,
|
| 575 |
+
375,
|
| 576 |
+
400,
|
| 577 |
+
425,
|
| 578 |
+
450,
|
| 579 |
+
475,
|
| 580 |
+
500,
|
| 581 |
+
525,
|
| 582 |
+
550,
|
| 583 |
+
575,
|
| 584 |
+
600,
|
| 585 |
+
625,
|
| 586 |
+
650,
|
| 587 |
+
675,
|
| 588 |
+
700,
|
| 589 |
+
725,
|
| 590 |
+
750,
|
| 591 |
+
775
|
| 592 |
+
],
|
| 593 |
+
"num_source_steps": 31,
|
| 594 |
+
"num_positives_pre_cap": 12143,
|
| 595 |
+
"num_negatives_pre_cap": 19601,
|
| 596 |
+
"positive": {
|
| 597 |
+
"loss": 0.8386550250702521,
|
| 598 |
+
"token_entropy": 0.027094298318338636,
|
| 599 |
+
"num_supervised_tokens": 4386490,
|
| 600 |
+
"kl_from_init": 3.172577502398244,
|
| 601 |
+
"kl_to_init": 0.4242703355377872,
|
| 602 |
+
"dead_units": {
|
| 603 |
+
"layer_0": {
|
| 604 |
+
"intermediate_size": 11008,
|
| 605 |
+
"dead_count": 0,
|
| 606 |
+
"dead_fraction": 0.0,
|
| 607 |
+
"mean_activation_freq": 0.9237279157321553,
|
| 608 |
+
"min_activation_freq": 0.7835399146014239
|
| 609 |
+
},
|
| 610 |
+
"layer_1": {
|
| 611 |
+
"intermediate_size": 11008,
|
| 612 |
+
"dead_count": 8763,
|
| 613 |
+
"dead_fraction": 0.7960574127906976,
|
| 614 |
+
"mean_activation_freq": 0.14735433270513157,
|
| 615 |
+
"min_activation_freq": 0.0
|
| 616 |
+
},
|
| 617 |
+
"layer_2": {
|
| 618 |
+
"intermediate_size": 11008,
|
| 619 |
+
"dead_count": 2499,
|
| 620 |
+
"dead_fraction": 0.22701671511627908,
|
| 621 |
+
"mean_activation_freq": 0.16650525008884307,
|
| 622 |
+
"min_activation_freq": 0.0
|
| 623 |
+
},
|
| 624 |
+
"layer_3": {
|
| 625 |
+
"intermediate_size": 11008,
|
| 626 |
+
"dead_count": 48,
|
| 627 |
+
"dead_fraction": 0.00436046511627907,
|
| 628 |
+
"mean_activation_freq": 0.3866349886896046,
|
| 629 |
+
"min_activation_freq": 0.0
|
| 630 |
+
},
|
| 631 |
+
"layer_4": {
|
| 632 |
+
"intermediate_size": 11008,
|
| 633 |
+
"dead_count": 1,
|
| 634 |
+
"dead_fraction": 9.084302325581395e-05,
|
| 635 |
+
"mean_activation_freq": 0.5526039419108709,
|
| 636 |
+
"min_activation_freq": 0.0
|
| 637 |
+
},
|
| 638 |
+
"layer_5": {
|
| 639 |
+
"intermediate_size": 11008,
|
| 640 |
+
"dead_count": 0,
|
| 641 |
+
"dead_fraction": 0.0,
|
| 642 |
+
"mean_activation_freq": 0.7150774923757379,
|
| 643 |
+
"min_activation_freq": 1.1398635355375255e-05
|
| 644 |
+
},
|
| 645 |
+
"layer_6": {
|
| 646 |
+
"intermediate_size": 11008,
|
| 647 |
+
"dead_count": 0,
|
| 648 |
+
"dead_fraction": 0.0,
|
| 649 |
+
"mean_activation_freq": 0.8694079081916265,
|
| 650 |
+
"min_activation_freq": 0.09600728600771916
|
| 651 |
+
},
|
| 652 |
+
"layer_7": {
|
| 653 |
+
"intermediate_size": 11008,
|
| 654 |
+
"dead_count": 0,
|
| 655 |
+
"dead_fraction": 0.0,
|
| 656 |
+
"mean_activation_freq": 0.8849198755004267,
|
| 657 |
+
"min_activation_freq": 0.03842274802860602
|
| 658 |
+
},
|
| 659 |
+
"layer_8": {
|
| 660 |
+
"intermediate_size": 11008,
|
| 661 |
+
"dead_count": 0,
|
| 662 |
+
"dead_fraction": 0.0,
|
| 663 |
+
"mean_activation_freq": 0.9407945491507036,
|
| 664 |
+
"min_activation_freq": 0.08709537694147257
|
| 665 |
+
},
|
| 666 |
+
"layer_9": {
|
| 667 |
+
"intermediate_size": 11008,
|
| 668 |
+
"dead_count": 0,
|
| 669 |
+
"dead_fraction": 0.0,
|
| 670 |
+
"mean_activation_freq": 0.9484981262432797,
|
| 671 |
+
"min_activation_freq": 0.25351089367580915
|
| 672 |
+
},
|
| 673 |
+
"layer_10": {
|
| 674 |
+
"intermediate_size": 11008,
|
| 675 |
+
"dead_count": 0,
|
| 676 |
+
"dead_fraction": 0.0,
|
| 677 |
+
"mean_activation_freq": 0.9733491323072144,
|
| 678 |
+
"min_activation_freq": 0.6666170446074197
|
| 679 |
+
},
|
| 680 |
+
"layer_11": {
|
| 681 |
+
"intermediate_size": 11008,
|
| 682 |
+
"dead_count": 0,
|
| 683 |
+
"dead_fraction": 0.0,
|
| 684 |
+
"mean_activation_freq": 0.9851466436468025,
|
| 685 |
+
"min_activation_freq": 0.9372151765990576
|
| 686 |
+
},
|
| 687 |
+
"layer_12": {
|
| 688 |
+
"intermediate_size": 11008,
|
| 689 |
+
"dead_count": 0,
|
| 690 |
+
"dead_fraction": 0.0,
|
| 691 |
+
"mean_activation_freq": 0.9867838763847554,
|
| 692 |
+
"min_activation_freq": 0.9203901068964024
|
| 693 |
+
},
|
| 694 |
+
"layer_13": {
|
| 695 |
+
"intermediate_size": 11008,
|
| 696 |
+
"dead_count": 0,
|
| 697 |
+
"dead_fraction": 0.0,
|
| 698 |
+
"mean_activation_freq": 0.9806985953015979,
|
| 699 |
+
"min_activation_freq": 0.9054863911692492
|
| 700 |
+
},
|
| 701 |
+
"layer_14": {
|
| 702 |
+
"intermediate_size": 11008,
|
| 703 |
+
"dead_count": 0,
|
| 704 |
+
"dead_fraction": 0.0,
|
| 705 |
+
"mean_activation_freq": 0.9829940961662837,
|
| 706 |
+
"min_activation_freq": 0.8945662705260926
|
| 707 |
+
},
|
| 708 |
+
"layer_15": {
|
| 709 |
+
"intermediate_size": 11008,
|
| 710 |
+
"dead_count": 0,
|
| 711 |
+
"dead_fraction": 0.0,
|
| 712 |
+
"mean_activation_freq": 0.9802970996608071,
|
| 713 |
+
"min_activation_freq": 0.9091284831379988
|
| 714 |
+
},
|
| 715 |
+
"layer_16": {
|
| 716 |
+
"intermediate_size": 11008,
|
| 717 |
+
"dead_count": 0,
|
| 718 |
+
"dead_fraction": 0.0,
|
| 719 |
+
"mean_activation_freq": 0.9797830398243268,
|
| 720 |
+
"min_activation_freq": 0.9080020699921806
|
| 721 |
+
},
|
| 722 |
+
"layer_17": {
|
| 723 |
+
"intermediate_size": 11008,
|
| 724 |
+
"dead_count": 0,
|
| 725 |
+
"dead_fraction": 0.0,
|
| 726 |
+
"mean_activation_freq": 0.9799441938303878,
|
| 727 |
+
"min_activation_freq": 0.9206105565041753
|
| 728 |
+
},
|
| 729 |
+
"layer_18": {
|
| 730 |
+
"intermediate_size": 11008,
|
| 731 |
+
"dead_count": 0,
|
| 732 |
+
"dead_fraction": 0.0,
|
| 733 |
+
"mean_activation_freq": 0.9804964731006852,
|
| 734 |
+
"min_activation_freq": 0.9190275140260209
|
| 735 |
+
},
|
| 736 |
+
"layer_19": {
|
| 737 |
+
"intermediate_size": 11008,
|
| 738 |
+
"dead_count": 0,
|
| 739 |
+
"dead_fraction": 0.0,
|
| 740 |
+
"mean_activation_freq": 0.9774391462851887,
|
| 741 |
+
"min_activation_freq": 0.9210671858365117
|
| 742 |
+
},
|
| 743 |
+
"layer_20": {
|
| 744 |
+
"intermediate_size": 11008,
|
| 745 |
+
"dead_count": 0,
|
| 746 |
+
"dead_fraction": 0.0,
|
| 747 |
+
"mean_activation_freq": 0.9799513759647288,
|
| 748 |
+
"min_activation_freq": 0.9115940079653664
|
| 749 |
+
},
|
| 750 |
+
"layer_21": {
|
| 751 |
+
"intermediate_size": 11008,
|
| 752 |
+
"dead_count": 0,
|
| 753 |
+
"dead_fraction": 0.0,
|
| 754 |
+
"mean_activation_freq": 0.9799060995661786,
|
| 755 |
+
"min_activation_freq": 0.921254579401754
|
| 756 |
+
},
|
| 757 |
+
"layer_22": {
|
| 758 |
+
"intermediate_size": 11008,
|
| 759 |
+
"dead_count": 0,
|
| 760 |
+
"dead_fraction": 0.0,
|
| 761 |
+
"mean_activation_freq": 0.979629108585097,
|
| 762 |
+
"min_activation_freq": 0.9265054747645612
|
| 763 |
+
},
|
| 764 |
+
"layer_23": {
|
| 765 |
+
"intermediate_size": 11008,
|
| 766 |
+
"dead_count": 0,
|
| 767 |
+
"dead_fraction": 0.0,
|
| 768 |
+
"mean_activation_freq": 0.9796331367518274,
|
| 769 |
+
"min_activation_freq": 0.9393989271604404
|
| 770 |
+
},
|
| 771 |
+
"layer_24": {
|
| 772 |
+
"intermediate_size": 11008,
|
| 773 |
+
"dead_count": 0,
|
| 774 |
+
"dead_fraction": 0.0,
|
| 775 |
+
"mean_activation_freq": 0.9816847563161629,
|
| 776 |
+
"min_activation_freq": 0.9286003159701721
|
| 777 |
+
},
|
| 778 |
+
"layer_25": {
|
| 779 |
+
"intermediate_size": 11008,
|
| 780 |
+
"dead_count": 0,
|
| 781 |
+
"dead_fraction": 0.0,
|
| 782 |
+
"mean_activation_freq": 0.9837521738009444,
|
| 783 |
+
"min_activation_freq": 0.9521147888174828
|
| 784 |
+
},
|
| 785 |
+
"layer_26": {
|
| 786 |
+
"intermediate_size": 11008,
|
| 787 |
+
"dead_count": 0,
|
| 788 |
+
"dead_fraction": 0.0,
|
| 789 |
+
"mean_activation_freq": 0.9857214633871592,
|
| 790 |
+
"min_activation_freq": 0.9553718348839277
|
| 791 |
+
},
|
| 792 |
+
"layer_27": {
|
| 793 |
+
"intermediate_size": 11008,
|
| 794 |
+
"dead_count": 0,
|
| 795 |
+
"dead_fraction": 0.0,
|
| 796 |
+
"mean_activation_freq": 0.986976763785735,
|
| 797 |
+
"min_activation_freq": 0.9438186340331336
|
| 798 |
+
},
|
| 799 |
+
"layer_28": {
|
| 800 |
+
"intermediate_size": 11008,
|
| 801 |
+
"dead_count": 0,
|
| 802 |
+
"dead_fraction": 0.0,
|
| 803 |
+
"mean_activation_freq": 0.9873534233036128,
|
| 804 |
+
"min_activation_freq": 0.22868557776263027
|
| 805 |
+
},
|
| 806 |
+
"layer_29": {
|
| 807 |
+
"intermediate_size": 11008,
|
| 808 |
+
"dead_count": 0,
|
| 809 |
+
"dead_fraction": 0.0,
|
| 810 |
+
"mean_activation_freq": 0.988561791022277,
|
| 811 |
+
"min_activation_freq": 0.9606047204028734
|
| 812 |
+
},
|
| 813 |
+
"layer_30": {
|
| 814 |
+
"intermediate_size": 11008,
|
| 815 |
+
"dead_count": 0,
|
| 816 |
+
"dead_fraction": 0.0,
|
| 817 |
+
"mean_activation_freq": 0.9900943873527078,
|
| 818 |
+
"min_activation_freq": 0.5556805099293513
|
| 819 |
+
},
|
| 820 |
+
"layer_31": {
|
| 821 |
+
"intermediate_size": 11008,
|
| 822 |
+
"dead_count": 0,
|
| 823 |
+
"dead_fraction": 0.0,
|
| 824 |
+
"mean_activation_freq": 0.9909337736030283,
|
| 825 |
+
"min_activation_freq": 0.9473214346778404
|
| 826 |
+
},
|
| 827 |
+
"layer_32": {
|
| 828 |
+
"intermediate_size": 11008,
|
| 829 |
+
"dead_count": 0,
|
| 830 |
+
"dead_fraction": 0.0,
|
| 831 |
+
"mean_activation_freq": 0.9891818871818938,
|
| 832 |
+
"min_activation_freq": 0.6423377233277632
|
| 833 |
+
},
|
| 834 |
+
"layer_33": {
|
| 835 |
+
"intermediate_size": 11008,
|
| 836 |
+
"dead_count": 0,
|
| 837 |
+
"dead_fraction": 0.0,
|
| 838 |
+
"mean_activation_freq": 0.9871342829856758,
|
| 839 |
+
"min_activation_freq": 0.9250963754619297
|
| 840 |
+
},
|
| 841 |
+
"layer_34": {
|
| 842 |
+
"intermediate_size": 11008,
|
| 843 |
+
"dead_count": 0,
|
| 844 |
+
"dead_fraction": 0.0,
|
| 845 |
+
"mean_activation_freq": 0.9883110041453192,
|
| 846 |
+
"min_activation_freq": 0.8885370763412205
|
| 847 |
+
},
|
| 848 |
+
"layer_35": {
|
| 849 |
+
"intermediate_size": 11008,
|
| 850 |
+
"dead_count": 0,
|
| 851 |
+
"dead_fraction": 0.0,
|
| 852 |
+
"mean_activation_freq": 0.9918224986932327,
|
| 853 |
+
"min_activation_freq": 0.0075981023551860375
|
| 854 |
+
},
|
| 855 |
+
"_overall": {
|
| 856 |
+
"dead_count": 11311,
|
| 857 |
+
"intermediate_total": 396288,
|
| 858 |
+
"dead_fraction": 0.028542373223514213
|
| 859 |
+
}
|
| 860 |
+
},
|
| 861 |
+
"size": 12143,
|
| 862 |
+
"size_pre_filter": 12143,
|
| 863 |
+
"skipped_long": 0
|
| 864 |
+
},
|
| 865 |
+
"negative": {
|
| 866 |
+
"loss": 1.2613379896533514,
|
| 867 |
+
"token_entropy": 0.04655036671746407,
|
| 868 |
+
"num_supervised_tokens": 8511791,
|
| 869 |
+
"kl_from_init": 2.9739833031196854,
|
| 870 |
+
"kl_to_init": 0.41306599295375773,
|
| 871 |
+
"dead_units": {
|
| 872 |
+
"layer_0": {
|
| 873 |
+
"intermediate_size": 11008,
|
| 874 |
+
"dead_count": 0,
|
| 875 |
+
"dead_fraction": 0.0,
|
| 876 |
+
"mean_activation_freq": 0.9240203550139181,
|
| 877 |
+
"min_activation_freq": 0.7855268062855397
|
| 878 |
+
},
|
| 879 |
+
"layer_1": {
|
| 880 |
+
"intermediate_size": 11008,
|
| 881 |
+
"dead_count": 1045,
|
| 882 |
+
"dead_fraction": 0.09493095930232558,
|
| 883 |
+
"mean_activation_freq": 0.1471531651917077,
|
| 884 |
+
"min_activation_freq": 0.0
|
| 885 |
+
},
|
| 886 |
+
"layer_2": {
|
| 887 |
+
"intermediate_size": 11008,
|
| 888 |
+
"dead_count": 630,
|
| 889 |
+
"dead_fraction": 0.05723110465116279,
|
| 890 |
+
"mean_activation_freq": 0.16644100589995048,
|
| 891 |
+
"min_activation_freq": 0.0
|
| 892 |
+
},
|
| 893 |
+
"layer_3": {
|
| 894 |
+
"intermediate_size": 11008,
|
| 895 |
+
"dead_count": 0,
|
| 896 |
+
"dead_fraction": 0.0,
|
| 897 |
+
"mean_activation_freq": 0.38703288791431234,
|
| 898 |
+
"min_activation_freq": 7.049045259687414e-07
|
| 899 |
+
},
|
| 900 |
+
"layer_4": {
|
| 901 |
+
"intermediate_size": 11008,
|
| 902 |
+
"dead_count": 0,
|
| 903 |
+
"dead_fraction": 0.0,
|
| 904 |
+
"mean_activation_freq": 0.5535366651951626,
|
| 905 |
+
"min_activation_freq": 6.814077084364501e-06
|
| 906 |
+
},
|
| 907 |
+
"layer_5": {
|
| 908 |
+
"intermediate_size": 11008,
|
| 909 |
+
"dead_count": 0,
|
| 910 |
+
"dead_fraction": 0.0,
|
| 911 |
+
"mean_activation_freq": 0.7152893019455272,
|
| 912 |
+
"min_activation_freq": 3.007592644133297e-05
|
| 913 |
+
},
|
| 914 |
+
"layer_6": {
|
| 915 |
+
"intermediate_size": 11008,
|
| 916 |
+
"dead_count": 0,
|
| 917 |
+
"dead_fraction": 0.0,
|
| 918 |
+
"mean_activation_freq": 0.8689796278127428,
|
| 919 |
+
"min_activation_freq": 0.09508915338734233
|
| 920 |
+
},
|
| 921 |
+
"layer_7": {
|
| 922 |
+
"intermediate_size": 11008,
|
| 923 |
+
"dead_count": 0,
|
| 924 |
+
"dead_fraction": 0.0,
|
| 925 |
+
"mean_activation_freq": 0.885919360497421,
|
| 926 |
+
"min_activation_freq": 0.041131766510714374
|
| 927 |
+
},
|
| 928 |
+
"layer_8": {
|
| 929 |
+
"intermediate_size": 11008,
|
| 930 |
+
"dead_count": 0,
|
| 931 |
+
"dead_fraction": 0.0,
|
| 932 |
+
"mean_activation_freq": 0.9408281318723496,
|
| 933 |
+
"min_activation_freq": 0.09025844267087856
|
| 934 |
+
},
|
| 935 |
+
"layer_9": {
|
| 936 |
+
"intermediate_size": 11008,
|
| 937 |
+
"dead_count": 0,
|
| 938 |
+
"dead_fraction": 0.0,
|
| 939 |
+
"mean_activation_freq": 0.9490171990036944,
|
| 940 |
+
"min_activation_freq": 0.267527362925147
|
| 941 |
+
},
|
| 942 |
+
"layer_10": {
|
| 943 |
+
"intermediate_size": 11008,
|
| 944 |
+
"dead_count": 0,
|
| 945 |
+
"dead_fraction": 0.0,
|
| 946 |
+
"mean_activation_freq": 0.9734657604344181,
|
| 947 |
+
"min_activation_freq": 0.6740499149943884
|
| 948 |
+
},
|
| 949 |
+
"layer_11": {
|
| 950 |
+
"intermediate_size": 11008,
|
| 951 |
+
"dead_count": 0,
|
| 952 |
+
"dead_fraction": 0.0,
|
| 953 |
+
"mean_activation_freq": 0.9851154419789937,
|
| 954 |
+
"min_activation_freq": 0.9352177467703331
|
| 955 |
+
},
|
| 956 |
+
"layer_12": {
|
| 957 |
+
"intermediate_size": 11008,
|
| 958 |
+
"dead_count": 0,
|
| 959 |
+
"dead_fraction": 0.0,
|
| 960 |
+
"mean_activation_freq": 0.9867623353499616,
|
| 961 |
+
"min_activation_freq": 0.9196131577948754
|
| 962 |
+
},
|
| 963 |
+
"layer_13": {
|
| 964 |
+
"intermediate_size": 11008,
|
| 965 |
+
"dead_count": 0,
|
| 966 |
+
"dead_fraction": 0.0,
|
| 967 |
+
"mean_activation_freq": 0.9804969349000903,
|
| 968 |
+
"min_activation_freq": 0.9046273575091306
|
| 969 |
+
},
|
| 970 |
+
"layer_14": {
|
| 971 |
+
"intermediate_size": 11008,
|
| 972 |
+
"dead_count": 0,
|
| 973 |
+
"dead_fraction": 0.0,
|
| 974 |
+
"mean_activation_freq": 0.9828480697611489,
|
| 975 |
+
"min_activation_freq": 0.8956286638147013
|
| 976 |
+
},
|
| 977 |
+
"layer_15": {
|
| 978 |
+
"intermediate_size": 11008,
|
| 979 |
+
"dead_count": 0,
|
| 980 |
+
"dead_fraction": 0.0,
|
| 981 |
+
"mean_activation_freq": 0.98016437142951,
|
| 982 |
+
"min_activation_freq": 0.9112155126929221
|
| 983 |
+
},
|
| 984 |
+
"layer_16": {
|
| 985 |
+
"intermediate_size": 11008,
|
| 986 |
+
"dead_count": 0,
|
| 987 |
+
"dead_fraction": 0.0,
|
| 988 |
+
"mean_activation_freq": 0.9797215766779925,
|
| 989 |
+
"min_activation_freq": 0.907227515337254
|
| 990 |
+
},
|
| 991 |
+
"layer_17": {
|
| 992 |
+
"intermediate_size": 11008,
|
| 993 |
+
"dead_count": 0,
|
| 994 |
+
"dead_fraction": 0.0,
|
| 995 |
+
"mean_activation_freq": 0.9798848378085928,
|
| 996 |
+
"min_activation_freq": 0.9213811758300926
|
| 997 |
+
},
|
| 998 |
+
"layer_18": {
|
| 999 |
+
"intermediate_size": 11008,
|
| 1000 |
+
"dead_count": 0,
|
| 1001 |
+
"dead_fraction": 0.0,
|
| 1002 |
+
"mean_activation_freq": 0.9804610396051346,
|
| 1003 |
+
"min_activation_freq": 0.919059455289727
|
| 1004 |
+
},
|
| 1005 |
+
"layer_19": {
|
| 1006 |
+
"intermediate_size": 11008,
|
| 1007 |
+
"dead_count": 0,
|
| 1008 |
+
"dead_fraction": 0.0,
|
| 1009 |
+
"mean_activation_freq": 0.9773634239997302,
|
| 1010 |
+
"min_activation_freq": 0.9214577754552479
|
| 1011 |
+
},
|
| 1012 |
+
"layer_20": {
|
| 1013 |
+
"intermediate_size": 11008,
|
| 1014 |
+
"dead_count": 0,
|
| 1015 |
+
"dead_fraction": 0.0,
|
| 1016 |
+
"mean_activation_freq": 0.9799163235120683,
|
| 1017 |
+
"min_activation_freq": 0.9172910848022466
|
| 1018 |
+
},
|
| 1019 |
+
"layer_21": {
|
| 1020 |
+
"intermediate_size": 11008,
|
| 1021 |
+
"dead_count": 0,
|
| 1022 |
+
"dead_fraction": 0.0,
|
| 1023 |
+
"mean_activation_freq": 0.979755411604299,
|
| 1024 |
+
"min_activation_freq": 0.9205088564792063
|
| 1025 |
+
},
|
| 1026 |
+
"layer_22": {
|
| 1027 |
+
"intermediate_size": 11008,
|
| 1028 |
+
"dead_count": 0,
|
| 1029 |
+
"dead_fraction": 0.0,
|
| 1030 |
+
"mean_activation_freq": 0.979381594879184,
|
| 1031 |
+
"min_activation_freq": 0.928913315658244
|
| 1032 |
+
},
|
| 1033 |
+
"layer_23": {
|
| 1034 |
+
"intermediate_size": 11008,
|
| 1035 |
+
"dead_count": 0,
|
| 1036 |
+
"dead_fraction": 0.0,
|
| 1037 |
+
"mean_activation_freq": 0.9792993795402529,
|
| 1038 |
+
"min_activation_freq": 0.9395880373472516
|
| 1039 |
+
},
|
| 1040 |
+
"layer_24": {
|
| 1041 |
+
"intermediate_size": 11008,
|
| 1042 |
+
"dead_count": 0,
|
| 1043 |
+
"dead_fraction": 0.0,
|
| 1044 |
+
"mean_activation_freq": 0.9814490544210215,
|
| 1045 |
+
"min_activation_freq": 0.9300873341462449
|
| 1046 |
+
},
|
| 1047 |
+
"layer_25": {
|
| 1048 |
+
"intermediate_size": 11008,
|
| 1049 |
+
"dead_count": 0,
|
| 1050 |
+
"dead_fraction": 0.0,
|
| 1051 |
+
"mean_activation_freq": 0.9834863054719325,
|
| 1052 |
+
"min_activation_freq": 0.9531357149159325
|
| 1053 |
+
},
|
| 1054 |
+
"layer_26": {
|
| 1055 |
+
"intermediate_size": 11008,
|
| 1056 |
+
"dead_count": 0,
|
| 1057 |
+
"dead_fraction": 0.0,
|
| 1058 |
+
"mean_activation_freq": 0.985500215408014,
|
| 1059 |
+
"min_activation_freq": 0.9555878427936024
|
| 1060 |
+
},
|
| 1061 |
+
"layer_27": {
|
| 1062 |
+
"intermediate_size": 11008,
|
| 1063 |
+
"dead_count": 0,
|
| 1064 |
+
"dead_fraction": 0.0,
|
| 1065 |
+
"mean_activation_freq": 0.9867909490434921,
|
| 1066 |
+
"min_activation_freq": 0.9403942131567845
|
| 1067 |
+
},
|
| 1068 |
+
"layer_28": {
|
| 1069 |
+
"intermediate_size": 11008,
|
| 1070 |
+
"dead_count": 0,
|
| 1071 |
+
"dead_fraction": 0.0,
|
| 1072 |
+
"mean_activation_freq": 0.9872282846057275,
|
| 1073 |
+
"min_activation_freq": 0.23535951481891415
|
| 1074 |
+
},
|
| 1075 |
+
"layer_29": {
|
| 1076 |
+
"intermediate_size": 11008,
|
| 1077 |
+
"dead_count": 0,
|
| 1078 |
+
"dead_fraction": 0.0,
|
| 1079 |
+
"mean_activation_freq": 0.988443814924251,
|
| 1080 |
+
"min_activation_freq": 0.959926177698677
|
| 1081 |
+
},
|
| 1082 |
+
"layer_30": {
|
| 1083 |
+
"intermediate_size": 11008,
|
| 1084 |
+
"dead_count": 0,
|
| 1085 |
+
"dead_fraction": 0.0,
|
| 1086 |
+
"mean_activation_freq": 0.9900132277955492,
|
| 1087 |
+
"min_activation_freq": 0.5775554169504397
|
| 1088 |
+
},
|
| 1089 |
+
"layer_31": {
|
| 1090 |
+
"intermediate_size": 11008,
|
| 1091 |
+
"dead_count": 0,
|
| 1092 |
+
"dead_fraction": 0.0,
|
| 1093 |
+
"mean_activation_freq": 0.9909034724774864,
|
| 1094 |
+
"min_activation_freq": 0.9489783055058565
|
| 1095 |
+
},
|
| 1096 |
+
"layer_32": {
|
| 1097 |
+
"intermediate_size": 11008,
|
| 1098 |
+
"dead_count": 0,
|
| 1099 |
+
"dead_fraction": 0.0,
|
| 1100 |
+
"mean_activation_freq": 0.9891706005520413,
|
| 1101 |
+
"min_activation_freq": 0.6691555279024121
|
| 1102 |
+
},
|
| 1103 |
+
"layer_33": {
|
| 1104 |
+
"intermediate_size": 11008,
|
| 1105 |
+
"dead_count": 0,
|
| 1106 |
+
"dead_fraction": 0.0,
|
| 1107 |
+
"mean_activation_freq": 0.9871393447542528,
|
| 1108 |
+
"min_activation_freq": 0.9260819491456028
|
| 1109 |
+
},
|
| 1110 |
+
"layer_34": {
|
| 1111 |
+
"intermediate_size": 11008,
|
| 1112 |
+
"dead_count": 0,
|
| 1113 |
+
"dead_fraction": 0.0,
|
| 1114 |
+
"mean_activation_freq": 0.9882501677852071,
|
| 1115 |
+
"min_activation_freq": 0.8984714262838456
|
| 1116 |
+
},
|
| 1117 |
+
"layer_35": {
|
| 1118 |
+
"intermediate_size": 11008,
|
| 1119 |
+
"dead_count": 0,
|
| 1120 |
+
"dead_fraction": 0.0,
|
| 1121 |
+
"mean_activation_freq": 0.9921358226794929,
|
| 1122 |
+
"min_activation_freq": 0.016832297691519917
|
| 1123 |
+
},
|
| 1124 |
+
"_overall": {
|
| 1125 |
+
"dead_count": 1675,
|
| 1126 |
+
"intermediate_total": 396288,
|
| 1127 |
+
"dead_fraction": 0.00422672399870801
|
| 1128 |
+
}
|
| 1129 |
+
},
|
| 1130 |
+
"size": 19601,
|
| 1131 |
+
"size_pre_filter": 19601,
|
| 1132 |
+
"skipped_long": 0
|
| 1133 |
+
}
|
| 1134 |
+
},
|
| 1135 |
+
"new_data": {
|
| 1136 |
+
"num_records": 0,
|
| 1137 |
+
"source_steps": [],
|
| 1138 |
+
"num_source_steps": 0,
|
| 1139 |
+
"num_positives_pre_cap": 0,
|
| 1140 |
+
"num_negatives_pre_cap": 0,
|
| 1141 |
+
"positive": {
|
| 1142 |
+
"size": 0
|
| 1143 |
+
},
|
| 1144 |
+
"negative": {
|
| 1145 |
+
"size": 0
|
| 1146 |
+
}
|
| 1147 |
+
}
|
| 1148 |
+
}
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_800/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"eos_token_id": 151643,
|
| 4 |
+
"max_new_tokens": 2048,
|
| 5 |
+
"transformers_version": "4.57.6"
|
| 6 |
+
}
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_800/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_800/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8fc1de3a344328f060df68e7ca8fe83714bc2b9a2fb6202b090e9a1735925376
|
| 3 |
+
size 4978997168
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_800/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d73806b6f5a4d42146bb391b28412e3e1e3687217b8c2ce212651bac933dcb84
|
| 3 |
+
size 1815259824
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_800/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,443 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 3397103616,
|
| 4 |
+
"total_size": 6794207232
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 22 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 24 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 34 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 44 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 48 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 49 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 59 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 73 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 84 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 85 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 94 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 97 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 104 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 109 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 117 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 130 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 142 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.layers.2.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 154 |
+
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 155 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 164 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 167 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 176 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 177 |
+
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 178 |
+
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 179 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 181 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 188 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 191 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 192 |
+
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 193 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 200 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 201 |
+
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 202 |
+
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 203 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 205 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 212 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 213 |
+
"model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 214 |
+
"model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 215 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 216 |
+
"model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 217 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 224 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 225 |
+
"model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 226 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 228 |
+
"model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 229 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 236 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 237 |
+
"model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 238 |
+
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 240 |
+
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 248 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 249 |
+
"model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 250 |
+
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 251 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 252 |
+
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 253 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 260 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 261 |
+
"model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 265 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 267 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 271 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 272 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 274 |
+
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 275 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 276 |
+
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 277 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 278 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 279 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 280 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 281 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 282 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 283 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 288 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 292 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 294 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 295 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 296 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 297 |
+
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 298 |
+
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 299 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 300 |
+
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 301 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 302 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 303 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 304 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 305 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 306 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 307 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 308 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 309 |
+
"model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 310 |
+
"model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 311 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 312 |
+
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 313 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 314 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 315 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 316 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 317 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 318 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 319 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 320 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 323 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 324 |
+
"model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 325 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 326 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 327 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 328 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 329 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 330 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 331 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 332 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 333 |
+
"model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 334 |
+
"model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 335 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 336 |
+
"model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 337 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 338 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 339 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 340 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 341 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 342 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 346 |
+
"model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 348 |
+
"model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 349 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 350 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 351 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 353 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 354 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 355 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 356 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 357 |
+
"model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 362 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 363 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 365 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 366 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 367 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 373 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 374 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 378 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 385 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 395 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 396 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 397 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 398 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 400 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 403 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 405 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 406 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 407 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 408 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 409 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 410 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 411 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 412 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 413 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 415 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 416 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 417 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 418 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 419 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 420 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 421 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 422 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 423 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 424 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 425 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 426 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 427 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 428 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 429 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 430 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 431 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 432 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 433 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 434 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 435 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 436 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 437 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 438 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 439 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 440 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 441 |
+
"model.norm.weight": "model-00002-of-00002.safetensors"
|
| 442 |
+
}
|
| 443 |
+
}
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_800/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_800/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_800/tokenizer_config.json
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"clean_up_tokenization_spaces": false,
|
| 199 |
+
"eos_token": "<|endoftext|>",
|
| 200 |
+
"errors": "replace",
|
| 201 |
+
"extra_special_tokens": {},
|
| 202 |
+
"model_max_length": 131072,
|
| 203 |
+
"pad_token": "<|endoftext|>",
|
| 204 |
+
"split_special_tokens": false,
|
| 205 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 206 |
+
"unk_token": null
|
| 207 |
+
}
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_800/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_900/added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_900/chat_template.jinja
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'You are a helpful assistant.' }}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 9 |
+
{%- for tool in tools %}
|
| 10 |
+
{{- "\n" }}
|
| 11 |
+
{{- tool | tojson }}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 14 |
+
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endif %}
|
| 21 |
+
{%- for message in messages %}
|
| 22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
+
{%- elif message.role == "assistant" %}
|
| 25 |
+
{{- '<|im_start|>' + message.role }}
|
| 26 |
+
{%- if message.content %}
|
| 27 |
+
{{- '\n' + message.content }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- for tool_call in message.tool_calls %}
|
| 30 |
+
{%- if tool_call.function is defined %}
|
| 31 |
+
{%- set tool_call = tool_call.function %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
+
{{- tool_call.name }}
|
| 35 |
+
{{- '", "arguments": ' }}
|
| 36 |
+
{{- tool_call.arguments | tojson }}
|
| 37 |
+
{{- '}\n</tool_call>' }}
|
| 38 |
+
{%- endfor %}
|
| 39 |
+
{{- '<|im_end|>\n' }}
|
| 40 |
+
{%- elif message.role == "tool" %}
|
| 41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
+
{{- '<|im_start|>user' }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{{- '\n<tool_response>\n' }}
|
| 45 |
+
{{- message.content }}
|
| 46 |
+
{{- '\n</tool_response>' }}
|
| 47 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
+
{{- '<|im_end|>\n' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{%- if add_generation_prompt %}
|
| 53 |
+
{{- '<|im_start|>assistant\n' }}
|
| 54 |
+
{%- endif %}
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_900/config.json
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"dtype": "bfloat16",
|
| 7 |
+
"eos_token_id": 151643,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 2048,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 11008,
|
| 12 |
+
"layer_types": [
|
| 13 |
+
"full_attention",
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention"
|
| 49 |
+
],
|
| 50 |
+
"max_position_embeddings": 32768,
|
| 51 |
+
"max_window_layers": 36,
|
| 52 |
+
"model_type": "qwen2",
|
| 53 |
+
"num_attention_heads": 16,
|
| 54 |
+
"num_hidden_layers": 36,
|
| 55 |
+
"num_key_value_heads": 2,
|
| 56 |
+
"pad_token_id": 151643,
|
| 57 |
+
"rms_norm_eps": 1e-06,
|
| 58 |
+
"rope_scaling": null,
|
| 59 |
+
"rope_theta": 1000000.0,
|
| 60 |
+
"sliding_window": null,
|
| 61 |
+
"tie_word_embeddings": true,
|
| 62 |
+
"transformers_version": "4.57.6",
|
| 63 |
+
"use_cache": true,
|
| 64 |
+
"use_mrope": false,
|
| 65 |
+
"use_sliding_window": false,
|
| 66 |
+
"vocab_size": 151936
|
| 67 |
+
}
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_900/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"eos_token_id": 151643,
|
| 4 |
+
"max_new_tokens": 2048,
|
| 5 |
+
"transformers_version": "4.57.6"
|
| 6 |
+
}
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_900/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_900/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f10764e87e8d10538fcb745009979b111063ba20a1ab411dcf2d9f3e8b5ae45
|
| 3 |
+
size 4976422832
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_900/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38992a7156dc1e08541acb09db4fe0ca7e5bb877a630b9a1b58cb8dbad213118
|
| 3 |
+
size 1817834216
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_900/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,443 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 3397103616,
|
| 4 |
+
"total_size": 6794207232
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 20 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 22 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.1.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 25 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 32 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 34 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 44 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 47 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 49 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 68 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 85 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 129 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 153 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 156 |
+
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 157 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 164 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 167 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 176 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 177 |
+
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 178 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 179 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 181 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 188 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 189 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 200 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 201 |
+
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 202 |
+
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 203 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 204 |
+
"model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 205 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 212 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 213 |
+
"model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 214 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 215 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 216 |
+
"model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 217 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 224 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 225 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 229 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 236 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 237 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 239 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 241 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 248 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 250 |
+
"model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 251 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 252 |
+
"model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 253 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 260 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 266 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 270 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 272 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 274 |
+
"model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 275 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 276 |
+
"model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 277 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 278 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 279 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 280 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 281 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 282 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 283 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 285 |
+
"model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 286 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 292 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 294 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 295 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 296 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 298 |
+
"model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 299 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 300 |
+
"model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 302 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 303 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 304 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 305 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 306 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 307 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 308 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 309 |
+
"model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 310 |
+
"model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 311 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 312 |
+
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 313 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 314 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 315 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 316 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 317 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 318 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 319 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 320 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 323 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 324 |
+
"model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 325 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 326 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 327 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 328 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 329 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 330 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 331 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 332 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 333 |
+
"model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 334 |
+
"model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 335 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 336 |
+
"model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 337 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 338 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 339 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 340 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 341 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 343 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 346 |
+
"model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 348 |
+
"model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 349 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 350 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 351 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 353 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 354 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 355 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 356 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 358 |
+
"model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 363 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 364 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 365 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 366 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 367 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 368 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 369 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 371 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 374 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 379 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 385 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 392 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 394 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 396 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 404 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 405 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 406 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 407 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 408 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 409 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 410 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 411 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 412 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 413 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 415 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 416 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 417 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 418 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 419 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 420 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 421 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 422 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 423 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 424 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 425 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 426 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 427 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 428 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 429 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 430 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 431 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 432 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 433 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 434 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 435 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 436 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 437 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 438 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 439 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 440 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 441 |
+
"model.norm.weight": "model-00001-of-00002.safetensors"
|
| 442 |
+
}
|
| 443 |
+
}
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_900/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_900/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_900/tokenizer_config.json
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"clean_up_tokenization_spaces": false,
|
| 199 |
+
"eos_token": "<|endoftext|>",
|
| 200 |
+
"errors": "replace",
|
| 201 |
+
"extra_special_tokens": {},
|
| 202 |
+
"model_max_length": 131072,
|
| 203 |
+
"pad_token": "<|endoftext|>",
|
| 204 |
+
"split_special_tokens": false,
|
| 205 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 206 |
+
"unk_token": null
|
| 207 |
+
}
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_900/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_950/added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_950/chat_template.jinja
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'You are a helpful assistant.' }}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 9 |
+
{%- for tool in tools %}
|
| 10 |
+
{{- "\n" }}
|
| 11 |
+
{{- tool | tojson }}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 14 |
+
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endif %}
|
| 21 |
+
{%- for message in messages %}
|
| 22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
+
{%- elif message.role == "assistant" %}
|
| 25 |
+
{{- '<|im_start|>' + message.role }}
|
| 26 |
+
{%- if message.content %}
|
| 27 |
+
{{- '\n' + message.content }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- for tool_call in message.tool_calls %}
|
| 30 |
+
{%- if tool_call.function is defined %}
|
| 31 |
+
{%- set tool_call = tool_call.function %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
+
{{- tool_call.name }}
|
| 35 |
+
{{- '", "arguments": ' }}
|
| 36 |
+
{{- tool_call.arguments | tojson }}
|
| 37 |
+
{{- '}\n</tool_call>' }}
|
| 38 |
+
{%- endfor %}
|
| 39 |
+
{{- '<|im_end|>\n' }}
|
| 40 |
+
{%- elif message.role == "tool" %}
|
| 41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
+
{{- '<|im_start|>user' }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{{- '\n<tool_response>\n' }}
|
| 45 |
+
{{- message.content }}
|
| 46 |
+
{{- '\n</tool_response>' }}
|
| 47 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
+
{{- '<|im_end|>\n' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{%- if add_generation_prompt %}
|
| 53 |
+
{{- '<|im_start|>assistant\n' }}
|
| 54 |
+
{%- endif %}
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_950/config.json
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"dtype": "bfloat16",
|
| 7 |
+
"eos_token_id": 151643,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 2048,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 11008,
|
| 12 |
+
"layer_types": [
|
| 13 |
+
"full_attention",
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention"
|
| 49 |
+
],
|
| 50 |
+
"max_position_embeddings": 32768,
|
| 51 |
+
"max_window_layers": 36,
|
| 52 |
+
"model_type": "qwen2",
|
| 53 |
+
"num_attention_heads": 16,
|
| 54 |
+
"num_hidden_layers": 36,
|
| 55 |
+
"num_key_value_heads": 2,
|
| 56 |
+
"pad_token_id": 151643,
|
| 57 |
+
"rms_norm_eps": 1e-06,
|
| 58 |
+
"rope_scaling": null,
|
| 59 |
+
"rope_theta": 1000000.0,
|
| 60 |
+
"sliding_window": null,
|
| 61 |
+
"tie_word_embeddings": true,
|
| 62 |
+
"transformers_version": "4.57.6",
|
| 63 |
+
"use_cache": true,
|
| 64 |
+
"use_mrope": false,
|
| 65 |
+
"use_sliding_window": false,
|
| 66 |
+
"vocab_size": 151936
|
| 67 |
+
}
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_950/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"eos_token_id": 151643,
|
| 4 |
+
"max_new_tokens": 2048,
|
| 5 |
+
"transformers_version": "4.57.6"
|
| 6 |
+
}
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_950/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_950/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3e170c60fa3cc1e867e94a756ad5326199e5cad3e32ddeccb0eec0190d21129
|
| 3 |
+
size 4682368408
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_950/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48f63157995d4b298d69de0e475195fd1902fa5cc9c2ff5e4d4c4a4ba9fd2fc9
|
| 3 |
+
size 2111888576
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_950/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,443 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 3397103616,
|
| 4 |
+
"total_size": 6794207232
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00002-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 21 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 24 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 45 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 56 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 57 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 94 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 97 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 104 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 164 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 166 |
+
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 167 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 169 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 177 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 179 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 181 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 188 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 189 |
+
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 190 |
+
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 191 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 192 |
+
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 193 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 200 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 201 |
+
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 202 |
+
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 203 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 204 |
+
"model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 205 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 212 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 213 |
+
"model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 214 |
+
"model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 215 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 216 |
+
"model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 217 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 224 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 225 |
+
"model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 226 |
+
"model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 227 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 228 |
+
"model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 229 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 236 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 237 |
+
"model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 238 |
+
"model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 239 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 240 |
+
"model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 241 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 248 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 249 |
+
"model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 250 |
+
"model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 251 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 252 |
+
"model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 253 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 260 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 261 |
+
"model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 264 |
+
"model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 268 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 269 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 274 |
+
"model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 275 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 276 |
+
"model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 277 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 278 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 279 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 280 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 281 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 282 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 283 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 292 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 294 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 295 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 296 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 298 |
+
"model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 299 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 300 |
+
"model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 302 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 303 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 304 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 305 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 306 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 307 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 308 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 309 |
+
"model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 310 |
+
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 311 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 312 |
+
"model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 314 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 315 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 316 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 317 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 318 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 319 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 320 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 323 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 324 |
+
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 325 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 326 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 327 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 328 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 329 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 330 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 331 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 332 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 333 |
+
"model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 334 |
+
"model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 335 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 336 |
+
"model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 337 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 338 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 339 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 340 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 346 |
+
"model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 348 |
+
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 349 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 350 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 351 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 353 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 354 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 355 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 356 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 358 |
+
"model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 360 |
+
"model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 363 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 365 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 366 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 367 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 372 |
+
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 373 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 384 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 385 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 393 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 398 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 400 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 405 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 406 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 407 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 408 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 409 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 410 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 411 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 412 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 413 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 415 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 416 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 417 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 418 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 419 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 420 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 421 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 422 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 423 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 424 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 425 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 426 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 427 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 428 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 429 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 430 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 431 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 432 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 433 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 434 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 435 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 436 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 437 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 438 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 439 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 440 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 441 |
+
"model.norm.weight": "model-00001-of-00002.safetensors"
|
| 442 |
+
}
|
| 443 |
+
}
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_950/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_950/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_950/tokenizer_config.json
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"clean_up_tokenization_spaces": false,
|
| 199 |
+
"eos_token": "<|endoftext|>",
|
| 200 |
+
"errors": "replace",
|
| 201 |
+
"extra_special_tokens": {},
|
| 202 |
+
"model_max_length": 131072,
|
| 203 |
+
"pad_token": "<|endoftext|>",
|
| 204 |
+
"split_special_tokens": false,
|
| 205 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 206 |
+
"unk_token": null
|
| 207 |
+
}
|
rlrb_bs128_nobuf/checkpoints_hf_format/global_step_950/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|