Update config.json

config.json

@@ -1,41 +1,34 @@
 {
-  "_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
   "architectures": [
     "LlamaForCausalLM"
   ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 11008,
+  "max_length": 4096,
   "max_position_embeddings": 4096,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
-  "num_key_value_heads": 32,
-  "pretraining_tp": 1,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.30.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000,
   "quantization_config": {
     "bits": 4,
+    "group_size": 128,
     "damp_percent": 0.01,
     "desc_act": false,
-    "group_size": 128,
-    "is_marlin_format": false,
-    "model_file_base_name": null,
-    "model_name_or_path": null,
-    "quant_method": "gptq",
-    "static_groups": false,
     "sym": true,
-    "true_sequential": true
-  },
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.38.2",
-  "use_cache": true,
-  "vocab_size": 32000
-}
+    "true_sequential": true,
+    "model_name_or_path": null,
+    "model_file_base_name": "model",
+    "quant_method": "gptq"
+  }
+}