Trained with Unsloth

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "ale045/kaggle_math_model_v6",
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -17,9 +17,13 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
+  "pad_token_id": 128255,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
+  "rope_scaling": {
+    "factor": 1.5,
+    "type": "linear"
+  },
   "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 sha256:8e8320a464ed41961626f5db5f04be58e73dd8ff09064844293219f51db3a82b
+oid sha256:5f570b49215254c2f59b7c7c78b84667be6592c34edc43d3b21a6568b4470e89
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:139719d7110a6dd9634f9fe3c39fa6633dafb21c968d34e9df15137dc31f89b1
+oid sha256:8b955c8213fabc1320bd3ee4d69124f72d7e7178b0c769ee67995f849cbd641e
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ca9c591d53b39102a906c017ef308d0d9d41920922157c2b7d3b9cb62acfda0
+oid sha256:0ba1231da86c3cf7907f30f0c9adbfffce09babd5617ced6f89b22c30fb10791
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8519472654251766e8b20c08462409bdfcfcb2af79882af5401bf6e61d53c46
+oid sha256:5a4f031d2d22252e55bcaa3172f28371c9b1c8d26e162aff4ccff5d88480a506
 size 1168138808