Update config.json

config.json

@@ -1,36 +1,29 @@
-{
-  "_name_or_path": "Phi-3-mini-4k-instruct",
-  "architectures": [
-    "Phi3ForCausalLM"
-  ],
-  "attention_dropout": 0.0,
-  "auto_map": {
-    "AutoConfig": "configuration_phi3.Phi3Config",
-    "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
-  },
-  "bos_token_id": 1,
-  "embd_pdrop": 0.0,
-  "eos_token_id": 32000,
-  "hidden_act": "silu",
-  "hidden_size": 3072,
-  "initializer_range": 0.02,
-  "intermediate_size": 8192,
-  "max_position_embeddings": 4096,
-  "model_type": "phi3",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 32,
-  "original_max_position_embeddings": 4096,
-  "pad_token_id": 32000,
-  "resid_pdrop": 0.0,
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
-  "sliding_window": 2047,
-  "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.40.2",
-  "use_cache": true,
-  "attention_bias": false,
-  "vocab_size": 32064
-}
+{
+  "_name_or_path": "unsloth/Phi-3-mini-4k-instruct-bnb-4bit",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "head_dim": 96,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 4096,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 32009,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 2048,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0",
+  "unsloth_version": "2024.5",
+  "use_cache": true,
+  "vocab_size": 32064
+}