Trained with Unsloth

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "ale045/kaggle_math_model_v2",
+  "_name_or_path": "ale045/kaggle_math_model_v6",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -19,10 +19,7 @@
   "num_key_value_heads": 8,
   "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 sha256:587151faaf1db5da9c781c591567c5fd2d4a3a3528a8ba11ad6e4f47a85ce0b8
+oid sha256:39fb104013a5363e7fe3f86f66d80a2ceed227e9f73e9d9b88ecdeede5d88abb
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b778622e212e3fc3ccbae7639e569715000dad1b26ed1b756edce8ea34f6b7e6
+oid sha256:26373a12d2d86e9f1299dd5fb674ce9f0e3fe07332f346eb6d59fc8e60d24ab5
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:554c569aac057235575690e93c63a0018c01db218a2599e8780c97f628f615b2
+oid sha256:36bb7093eae4f081f7d52e63f0694dbfcb259042f2499f50e901068c2244a736
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fae6cb1c903495d97ecb9b9a3eeb890e4a1d7b160f13ab82275f979dbf954de2
+oid sha256:52e5806458e7367c6ecf75dcdb138a22194569db6ac29929553bdd01b3dac605
 size 1168138808