Update config.json

config.json

@@ -1,24 +1,25 @@
 {
-    "architectures": [
-      "LlamaForCausalLM"
-    ],
-    "bos_token_id": 1,
-    "eos_token_id": 2,
-    "hidden_act": "silu",
-    "hidden_size": 2048,
-    "initializer_range": 0.02,
-    "intermediate_size": 5504,
-    "max_position_embeddings": 2048,
-    "model_type": "llama",
-    "num_attention_heads": 32,
-    "num_hidden_layers": 27,
-    "num_key_value_heads": 32,
-    "pretraining_tp": 1,
-    "rms_norm_eps": 1e-05,
-    "rope_scaling": null,
-    "tie_word_embeddings": false,
-    "torch_dtype": "bfloat16",
-    "transformers_version": "4.31.0.dev0",
-    "use_cache": true,
-    "vocab_size": 32768
-  }
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 2048,
+  "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": 2048,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32768
+}