Trained with Unsloth

README.md

@@ -8,6 +8,7 @@ tags:
 - unsloth
 - mistral
 - trl
+- sft
 base_model: unsloth/mistral-7b-bnb-4bit
 ---
 

config.json

@@ -1,3 +1,28 @@
 {
-    "model_type": "mistral"
-}
+  "_name_or_path": "unsloth/mistral-7b-bnb-4bit",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.37.2",
+  "unsloth_version": "2024.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15ee04548f411a1740515f7a557634905130ac51d4969a5c8e7cfd4c1be72749
+oid sha256:8197f6dcfb4b25cf066cd9d536eebc29ef401325a3efe6773eeff1403117a2d6
 size 4943162240

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73b4f86de3735e003792a460e41ae7e5d4418ece51921d0463e2ab67d53c2f85
+oid sha256:c07d0dbd4011ecf13249660857c5a40e6e3f9ae68920959a178f3979ad492499
 size 4999819232

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd9f07ec4d6756d9d2a8d8e466390259d291d4c18e9e79c3e287b20464a001c2
+oid sha256:0c251e637c16c9ccbe0a3b1e6181a01213427ab329414c619d06db4487d28063
 size 4540516256