Update config.json

config.json

@@ -1,28 +1,25 @@
 {
-  "_name_or_path": "/raid/younes/gg-converted-ckpt/gemma-7b-it",
   "architectures": [
-    "GemmaForCausalLM"
+    "MistralForCausalLM"
   ],
-  "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 2,
-  "eos_token_id": 1,
-  "head_dim": 256,
-  "hidden_act": "gelu",
-  "hidden_size": 3072,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
   "initializer_range": 0.02,
-  "intermediate_size": 24576,
-  "max_position_embeddings": 8192,
-  "model_type": "gemma",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 28,
-  "num_key_value_heads": 16,
-  "pad_token_id": 0,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
+  "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": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.38.0.dev0",
+  "transformers_version": "4.36.0",
   "use_cache": true,
-  "vocab_size": 256000
+  "vocab_size": 32000
 }