Adding AWQ model

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--H-D-T--Buzz-8b-Large-v0.5/snapshots/a7a409bc713842e03edd52d7f1172b6ddfe1f738",
+  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--H-D-T--Buzz-8b-Large-v0.5/snapshots/5f4fdba951b221bec83bab6e3890ab1e9f9e0e09",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -11,7 +11,8 @@
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 14336,
-  "max_position_embeddings": 1048576,
+  "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": "4.40.2",
+  "transformers_version": "4.41.0",
   "use_cache": false,
   "vocab_size": 128256
 }

generation_config.json

@@ -5,5 +5,5 @@
   "max_length": 4096,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.40.2"
+  "transformers_version": "4.41.0"
 }