Update config.json

config.json

@@ -1,41 +1,14 @@
 {
-  "architectures": [
-    "GPTForCausalLM"
-  ],
-  "model_type": "gpt",
-  "vocab_size": 50257,
-  "n_positions": 1024,
-  "n_ctx": 1024,
-  "n_embd": 768,
-  "n_layer": 12,
-  "n_head": 12,
-  "activation_function": "gelu_new",
-  "resid_pdrop": 0.1,
-  "embd_pdrop": 0.1,
-  "attn_pdrop": 0.1,
-  "layer_norm_epsilon": 1e-5,
+  "model_type": "mistral",
+  "architectures": ["MistralForCausalLM"],
+  "hidden_size": 4096,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 32,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "layer_norm_eps": 1e-5,
   "initializer_range": 0.02,
-  "summary_type": "cls_index",
-  "summary_use_proj": true,
-  "summary_activation": "gelu",
-  "summary_proj_to_labels": true,
-  "summary_first_dropout": 0.1,
-  "scale_attn_weights": true,
   "use_cache": true,
-  "bos_token_id": 50256,
-  "eos_token_id": 50256,
-  "pad_token_id": 50256,
-  "max_length": 1024,
-  "min_length": 0,
-  "do_sample": false,
-  "early_stopping": false,
-  "num_beams": 1,
-  "temperature": 1.0,
-  "top_k": 50,
-  "top_p": 1.0,
-  "repetition_penalty": 1.0,
-  "length_penalty": 1.0,
-  "no_repeat_ngram_size": 0,
-  "num_return_sequences": 1
+  "vocab_size": 50257,
+  "tokenizer_class": "GPT2Tokenizer"
 }
-