mistral config

config.json

@@ -1,18 +1,15 @@
 {
-  "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
-  "architectures": [
-    "LlamaForCausalLM"
-  ],
-  "attention_bias": false,
+  "_name_or_path": "BioMistral/BioMistral-7B",
+  "architectures": ["MistralForCausalLM"],
   "attention_dropout": 0.0,
-  "bos_token_id": 128000,
-  "eos_token_id": 128001,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 14336,
-  "max_position_embeddings": 8192,
-  "model_type": "llama",
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
@@ -32,12 +29,12 @@
     "load_in_8bit": false,
     "quant_method": "bitsandbytes"
   },
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
-  "rope_theta": 500000.0,
+  "rms_norm_eps": 1e-5,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.40.0",
+  "transformers_version": "4.39.3",
   "use_cache": true,
-  "vocab_size": 128256
+  "vocab_size": 32000
 }