AWQ

.gitattributes

@@ -34,11 +34,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
-config.json filter=lfs diff=lfs merge=lfs -text
 generation_config.json filter=lfs diff=lfs merge=lfs -text
 model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
 special_tokens_map.json filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
 model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
 model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
-*.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -1,3 +1,38 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f9f29c14ee4f0817e1547b7844e8b0148d30e6190946d46097503ecf69004d8c
-size 1006
+{
+  "_name_or_path": "/root/.cache/huggingface/hub/models--Sao10K--L3-8B-Lunaris-v1/snapshots/8479c2a7ee119c935b9a02c921cc2a85b698dfe8",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "bits": 4,
+    "group_size": 128,
+    "modules_to_not_convert": null,
+    "quant_method": "awq_marlin",
+    "version": "marlin",
+    "zero_point": false
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.47.1",
+  "use_cache": false,
+  "vocab_size": 128256
+}