Upload model trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- config.json +91 -0
- generation_config.json +9 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Gemma2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"attn_logit_softcapping": 50.0,
|
| 8 |
+
"bos_token_id": 2,
|
| 9 |
+
"cache_implementation": "hybrid",
|
| 10 |
+
"dtype": "float16",
|
| 11 |
+
"eos_token_id": 1,
|
| 12 |
+
"final_logit_softcapping": 30.0,
|
| 13 |
+
"head_dim": 256,
|
| 14 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 15 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 16 |
+
"hidden_size": 3584,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 14336,
|
| 19 |
+
"layer_types": [
|
| 20 |
+
"sliding_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"sliding_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"sliding_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"sliding_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"sliding_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"sliding_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"sliding_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"sliding_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"sliding_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"sliding_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"sliding_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"sliding_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"sliding_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"sliding_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"sliding_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"sliding_attention",
|
| 51 |
+
"full_attention",
|
| 52 |
+
"sliding_attention",
|
| 53 |
+
"full_attention",
|
| 54 |
+
"sliding_attention",
|
| 55 |
+
"full_attention",
|
| 56 |
+
"sliding_attention",
|
| 57 |
+
"full_attention",
|
| 58 |
+
"sliding_attention",
|
| 59 |
+
"full_attention",
|
| 60 |
+
"sliding_attention",
|
| 61 |
+
"full_attention"
|
| 62 |
+
],
|
| 63 |
+
"max_position_embeddings": 8192,
|
| 64 |
+
"model_type": "gemma2",
|
| 65 |
+
"num_attention_heads": 16,
|
| 66 |
+
"num_hidden_layers": 42,
|
| 67 |
+
"num_key_value_heads": 8,
|
| 68 |
+
"pad_token_id": 0,
|
| 69 |
+
"quantization_config": {
|
| 70 |
+
"bnb_4bit_compute_dtype": "float16",
|
| 71 |
+
"bnb_4bit_quant_type": "nf4",
|
| 72 |
+
"bnb_4bit_use_double_quant": true,
|
| 73 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 74 |
+
"llm_int8_has_fp16_weight": false,
|
| 75 |
+
"llm_int8_skip_modules": null,
|
| 76 |
+
"llm_int8_threshold": 6.0,
|
| 77 |
+
"load_in_4bit": true,
|
| 78 |
+
"load_in_8bit": false,
|
| 79 |
+
"quant_method": "bitsandbytes"
|
| 80 |
+
},
|
| 81 |
+
"query_pre_attn_scalar": 256,
|
| 82 |
+
"rms_norm_eps": 1e-06,
|
| 83 |
+
"rope_scaling": null,
|
| 84 |
+
"rope_theta": 10000.0,
|
| 85 |
+
"sliding_window": 4096,
|
| 86 |
+
"sliding_window_size": 4096,
|
| 87 |
+
"transformers_version": "4.57.1",
|
| 88 |
+
"unsloth_version": "2025.11.3",
|
| 89 |
+
"use_cache": true,
|
| 90 |
+
"vocab_size": 256000
|
| 91 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 2,
|
| 4 |
+
"cache_implementation": "hybrid",
|
| 5 |
+
"eos_token_id": 1,
|
| 6 |
+
"max_length": 8192,
|
| 7 |
+
"pad_token_id": 0,
|
| 8 |
+
"transformers_version": "4.57.1"
|
| 9 |
+
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:050f9145106dcb8766f9b8e54055ee8399403e224de0df0e70bc86449b96d40f
|
| 3 |
+
size 4979101165
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e6dfd11de7d17f104cdab11917c3dc2d20b06c8c89bea20112bb2dbbf4c1ff9
|
| 3 |
+
size 1151605121
|
model.safetensors.index.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|