Hugging Face's logo

Blancy
/
DeepSeek-R1-Distill-Qwen-0.5B-GRPO

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
open-r1
trl
grpo
conversational
text-generation-inference
Model card Files
xet
 Community
Blancy commited on
Commit
9e097a3
·
verified ·
1 Parent(s): 882671c

Training in progress, epoch 0

Browse files
Files changed (3) hide show
  1. config.json +1 -1
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
config.json CHANGED
@@ -23,7 +23,7 @@
23
  "tie_word_embeddings": true,
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.49.0",
26
- "use_cache": true,
27
  "use_sliding_window": false,
28
  "vocab_size": 151936
29
  }
 
23
  "tie_word_embeddings": true,
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.49.0",
26
+ "use_cache": false,
27
  "use_sliding_window": false,
28
  "vocab_size": 151936
29
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d595ef52e00b00482db36600853bf829093289d0c0b2133bdc4dc31134ba542
3
  size 1260367448
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e10cecc9297656ff60f41f132bf48e088a01672dc3fe303daaaea864aa009db
3
  size 1260367448
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:393e5c6ecce922e126cc3f902b90c6e8cbb5733667982972cb703a87f21ce7f1
3
  size 10168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf71911342d3f714c62d3dca0aac5d532a2f782025a69b3063d42d8763772978
3
  size 10168