Trained with Unsloth

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "meta-llama/Meta-Llama-3-8B",
+  "_name_or_path": "ale045/kaggle_math_model_v6",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -20,10 +20,7 @@
   "pad_token_id": 128255,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
-  "rope_scaling": {
-    "factor": 1.5,
-    "type": "linear"
-  },
+  "rope_scaling": null,
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f570b49215254c2f59b7c7c78b84667be6592c34edc43d3b21a6568b4470e89
+oid sha256:2b6c6c0fb13a4d1339dcf683b8a23429d2e0b6536389cee5516d1f10080f67f7
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b955c8213fabc1320bd3ee4d69124f72d7e7178b0c769ee67995f849cbd641e
+oid sha256:8399582bdc9378583295bf199b9c7ccbb214efd6d6c4b86aa075bf49e269d95f
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ba1231da86c3cf7907f30f0c9adbfffce09babd5617ced6f89b22c30fb10791
+oid sha256:6031bb1312bccd31f33c51bd8a2e13afdb1a570d423c9ab4f682ae0791ec35e8
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a4f031d2d22252e55bcaa3172f28371c9b1c8d26e162aff4ccff5d88480a506
+oid sha256:bbdb734c059da15c59b7c5a8b714ebb3e9b98aae1c85a875052f6eb226d2d114
 size 1168138808