Hugging Face's logo

Blancy
/
Qwen3-1.7B-Open-R1-Code-GRPO

Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
open-r1
trl
grpo
conversational
text-generation-inference
Model card Files
xet
Community
Blancy commited on
Commit
287d796
·
verified ·
1 Parent(s): 21ce5f5

Training in progress, epoch 1

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
@@ -24,7 +24,7 @@
24
  "tie_word_embeddings": true,
25
  "torch_dtype": "bfloat16",
26
  "transformers_version": "4.52.3",
27
- "use_cache": true,
28
  "use_sliding_window": false,
29
  "vocab_size": 151936
30
  }
 
24
  "tie_word_embeddings": true,
25
  "torch_dtype": "bfloat16",
26
  "transformers_version": "4.52.3",
27
+ "use_cache": false,
28
  "use_sliding_window": false,
29
  "vocab_size": 151936
30
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:10a0e99b201648acb6ba458db99773a474c55d9ce92d72a203f30f6051dd1937
3
  size 4063515640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:583ed0b0856ae0d450158bc2eaa7ed174b9ae0593f19be2344a9497ba6cac4e8
3
  size 4063515640
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66bb1dd39935f18a98f0436e61fa9a767e1bedcbcb28b5b4d4a791a57719cde7
3
  size 7992
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c25c58deaba3051e9f79f5af1b37ef58d4601ca952c4964632b2cdc3b518b3d
3
  size 7992