Hugging Face's logo

chansung
/
Qwen2.5-1.5B-Open-R1-Code-GRPO

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
open-r1
trl
grpo
conversational
text-generation-inference
Model card Files
xet
Community
chansung commited on
Commit
999eaf6
·
verified ·
1 Parent(s): 082876a

Training in progress, step 50

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
@@ -22,7 +22,7 @@
22
  "tie_word_embeddings": true,
23
  "torch_dtype": "bfloat16",
24
  "transformers_version": "4.52.0.dev0",
25
- "use_cache": true,
26
  "use_sliding_window": false,
27
  "vocab_size": 151936
28
  }
 
22
  "tie_word_embeddings": true,
23
  "torch_dtype": "bfloat16",
24
  "transformers_version": "4.52.0.dev0",
25
+ "use_cache": false,
26
  "use_sliding_window": false,
27
  "vocab_size": 151936
28
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:376feea418d3c47f6e6af47a6f9b97481d01f6b868c948f853e61879cdf3058d
3
  size 3554214752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fab8332b2d114041741e0ebfba8fc83e28cbf909f880fd7db2b74fc53df5f4e2
3
  size 3554214752
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30a703cd7bcf137286d52530338f44db47720f935128105b3ed0f9b3ba2d25b9
3
  size 8376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3e01a3bc832597b0f629c6694e24bf8b02f9e65dbf0e8a33c3e90c5af1ea41b
3
  size 8376