Adding AWQ model

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/home/shaun/.cache/huggingface/hub/models--nbeerbower--llama-3-stinky-v2-8B/snapshots/f9ba3108c2ae60f2b96c6df00069bf9ebc23b561",
+  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--nbeerbower--llama-3-stinky-v2-8B/snapshots/f9ba3108c2ae60f2b96c6df00069bf9ebc23b561",
   "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": "4.40.1",
+  "transformers_version": "4.41.0",
   "use_cache": false,
   "vocab_size": 128256
 }

generation_config.json

@@ -3,6 +3,6 @@
   "bos_token_id": 128000,
   "do_sample": true,
   "eos_token_id": 128001,
-  "transformers_version": "4.40.1",
+  "transformers_version": "4.41.0",
   "use_cache": false
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce4b03258b7f96285c0e742fb26de52cbcd81bb4268efa11a23a13787e5910c8
+oid sha256:9baa99ccc3066466dcbf39e3cc82571600095041aa391612543a6b3b8ccbd467
 size 4677265296