Trained with Unsloth

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "unsloth/Meta-Llama-3.1-8B-bnb-4bit",
+  "_name_or_path": "unsloth/DeepSeek-R1-Distill-Llama-8B-unsloth-bnb-4bit",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -31,8 +31,9 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.47.1",
-  "unsloth_version": "2025.1.8",
+  "transformers_version": "4.48.3",
+  "unsloth_fixed": true,
+  "unsloth_version": "2025.2.12",
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -6,6 +6,6 @@
   "max_length": 131072,
   "pad_token_id": 128004,
   "temperature": 0.6,
-  "top_p": 0.9,
-  "transformers_version": "4.47.1"
+  "top_p": 0.95,
+  "transformers_version": "4.48.3"
 }

pytorch_model-00001-of-00004.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27f283779b4ba51df55d186b8732adb20c92d6499fa04daf2eebe4b82983395f
-size 4976718466
+oid sha256:127f56c2f3de7b09aa00835187acfb7726271bc9bb6ad3d17bafc173b6542376
+size 4976717570

pytorch_model-00002-of-00004.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28cbc02a92996e21cd21ed4114b235043e5f339c910cc4c2a547d491381f5bb7
-size 4999827206
+oid sha256:df7eaf90b0ec46cc35db7d639dadd03c1ba8a21c6c66e90107f95421e70bd94e
+size 4999826566

pytorch_model-00003-of-00004.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ae260848bed399227808f26e7186587ec5e9b13c9a0e161a3c778d6497dfdb4
+oid sha256:9f9953cd48ecf7c142216db5d4c2855ad47e427df2f3fd8fc6e6a2f387d45884
 size 4915939082

pytorch_model-00004-of-00004.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:452e7d020d51a567a4e7a846b5234699c534b07eb18a5d7684efc8617f31ce8f
+oid sha256:0d10301b034a5ea9f1ba82e6a93201ba0a8a8c25196d95ef0bfcc051673f0124
 size 1168140873