Hugging Face's logo

Julian-CF
/
Qwen2.5-1.5B-Open-R1-GRPO

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
open-r1
trl
grpo
conversational
text-generation-inference
Model card Files
xet
Community
Julian-CF commited on
Commit
b862bf2
·
verified ·
1 Parent(s): 0dc0fce

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": "4.51.2",
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": "4.51.2",
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 sha256:2a812b2de8e731dbb10daba452e41d02163a4a87f665fa867eb73f00342b1c0a
3
  size 3554214752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:100fc1b606d795347a18eb72268d6c7622d34311a865e2c2a0adf47211ce5598
3
  size 3554214752
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1fc2e3b02497cafdeb38a56a45c4abcb9e8e9d9d6a88616b1bf960dacd279b55
3
  size 8632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39acb2675c31a50877984c65fdabddb185f5b09ddf1ab888863f4bc366095c43
3
  size 8632