Update config.json

config.json

@@ -1,33 +1,26 @@
 {
-  "alibi": false,
-  "apply_residual_connection_post_layernorm": false,
+  "_name_or_path": "HuggingFaceH4/mistral-7b-anthropic",
   "architectures": [
-    "FalconForCausalLM"
+    "MistralForCausalLM"
   ],
   "attention_dropout": 0.0,
-  "auto_map": {
-    "AutoConfig": "configuration_falcon.FalconConfig",
-    "AutoModel": "modeling_falcon.FalconModel",
-    "AutoModelForSequenceClassification": "modeling_falcon.FalconForSequenceClassification",
-    "AutoModelForTokenClassification": "modeling_falcon.FalconForTokenClassification",
-    "AutoModelForQuestionAnswering": "modeling_falcon.FalconForQuestionAnswering",
-    "AutoModelForCausalLM": "modeling_falcon.FalconForCausalLM"
-  },
-  "bias": false,
-  "bos_token_id": 11,
-  "eos_token_id": 11,
-  "hidden_dropout": 0.0,
-  "hidden_size": 8192,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
   "initializer_range": 0.02,
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "falcon",
-  "new_decoder_architecture": true,
-  "num_attention_heads": 128,
-  "num_hidden_layers": 60,
-  "num_kv_heads": 8,
-  "parallel_attn": true,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.27.4",
+  "transformers_version": "4.39.3",
   "use_cache": true,
-  "vocab_size": 65024
-}
+  "vocab_size": 32002
+}