Update config.json

config.json

@@ -1,32 +1,19 @@
 {
-  "alibi": false,
-  "apply_residual_connection_post_layernorm": false,
-  "architectures": [
-    "RWForCausalLM"
-  ],
-  "attention_dropout": 0.0,
-  "auto_map": {
-    "AutoConfig": "configuration_RW.RWConfig",
-    "AutoModel": "modelling_RW.RWModel",
-    "AutoModelForSequenceClassification": "modelling_RW.RWForSequenceClassification",
-    "AutoModelForTokenClassification": "modelling_RW.RWForTokenClassification",
-    "AutoModelForQuestionAnswering": "modelling_RW.RWForQuestionAnswering",
-    "AutoModelForCausalLM": "modelling_RW.RWForCausalLM"
-  },
-  "bias": false,
-  "bos_token_id": 11,
-  "eos_token_id": 11,
-  "hidden_dropout": 0.0,
-  "hidden_size": 4544,
-  "initializer_range": 0.02,
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "RefinedWebModel",
-  "multi_query": true,
-  "n_head": 71,
-  "n_layer": 32,
-  "parallel_attn": true,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.27.4",
-  "use_cache": true,
-  "vocab_size": 65024
-}
+    "architectures": ["LLaMAForCausalLM"], 
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu", 
+    "hidden_size": 8192, 
+    "intermediate_size": 22016, 
+    "initializer_range": 0.02, 
+    "max_sequence_length": 2048, 
+    "model_type": "llama", 
+    "num_attention_heads": 64, 
+    "num_hidden_layers": 80, 
+    "pad_token_id": 0, 
+    "rms_norm_eps": 1e-05, 
+    "torch_dtype": "float16", 
+    "transformers_version": "4.28.0.dev0",
+    "use_cache": true, 
+    "vocab_size": 32000
+}