Upload quantized AWQ model

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--mlabonne--ChimeraLlama-3-8B-v3/snapshots/c8c1787e1426e3979ae82134f4eb7fa332f58ae0",
+  "_name_or_path": "/opt/openbet/inference/data/mlabonne-ChimeraLlama-3-8B-v3",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -12,6 +12,7 @@
   "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,
@@ -30,7 +31,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.38.2",
-  "use_cache": false,
+  "transformers_version": "4.44.2",
+  "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -3,6 +3,5 @@
   "bos_token_id": 128000,
   "do_sample": true,
   "eos_token_id": 128001,
-  "transformers_version": "4.38.2",
-  "use_cache": false
+  "transformers_version": "4.44.2"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e91c5029bc967a898aa8dcc7568d511dc7758038f6bee13f7c913225a7e6656e
+oid sha256:ae369237ef085a9570b3e3b34293faec0f9c6f75e2fb93e048106be45195cb0f
 size 4677265296

tokenizer.json

@@ -2407,6 +2407,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": false,
     "byte_fallback": false,
+    "ignore_merges": true,
     "vocab": {
       "!": 0,
       "\"": 1,