Trained with Unsloth

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "unsloth/mistral-7b-bnb-4bit",
+  "_name_or_path": "unsloth/mistral-7b-instruct-v0.2-bnb-4bit",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -15,10 +15,10 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
-  "pad_token_id": 2,
+  "pad_token_id": 0,
   "rms_norm_eps": 1e-05,
-  "rope_theta": 10000.0,
-  "sliding_window": 4096,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.41.0",

pytorch_model-00001-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:323b7b168c1d2146866920f5ae37106d87c8dba4d92f5cc95d98aa8900143fac
-size 4943185184
+oid sha256:2b4184dd3a010073f7c9cdc222ada9a64aec62efe4eeac6cd14e2a1809b98ee9
+size 4943185632

pytorch_model-00002-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07c0f8e3c2ef8894af815e4097229762e1edacb9ddbf1aceb2d5d9af6c8ee142
-size 4999843656
+oid sha256:bacc382577701592b8178da3e4a018da94b7ca2ae855567c2cf98443c76cf70a
+size 4999844360

pytorch_model-00003-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad54d2fe0615ca8a3362284c85aec7d0090a6d1435a23a405db2b57c75378ac3
+oid sha256:5583ebddcf1b7068fcc683edfb63f462427ba720d454be6a3297d5bbaba9ae12
 size 4540536454