Hugging Face's logo

Blancy
/
Qwen2.5-1.5B-Open-R1-GRPO

Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
open-r1
trl
grpo
conversational
text-generation-inference
Model card Files
xet
Community
1
Blancy commited on
Commit
aae2026
·
verified ·
1 Parent(s): 82444b2

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 sha256:6cdd42afc55fc15db5689e955148fb8eed3f0d977d2b4ac146ecef56b99f2272
3
  size 3554214752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:846a7ceb753a788e7482fe43fec79c96017f28422774cf5bb26d37454c35d242
3
  size 3554214752
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a77ee3f8245d6926bf339eb82556d091212bc8e4e28a798b7baf9857fc5648e
3
  size 7992
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12beb910020968fb508da8d19468f57a746cd676c0f4b3a9ca6e9c4a64a5555a
3
  size 7992