Hugging Face's logo

Jforeverss
/
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 Community
Jforeverss commited on
Commit
041788b
·
verified ·
1 Parent(s): 89e6220

Training in progress, epoch 1

Browse files
Files changed (4) hide show
  1. config.json +1 -1
  2. model.safetensors +1 -1
  3. tokenizer.json +2 -2
  4. training_args.bin +2 -2
config.json CHANGED
@@ -22,7 +22,7 @@
22
  "tie_word_embeddings": true,
23
  "torch_dtype": "bfloat16",
24
  "transformers_version": "4.51.2",
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": "4.51.2",
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:e372a4c4a0185a320162adfeb5c7c324202aefb71a6dd5f6f461fc1d466ce609
3
  size 3554214752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd2b9eec59cdbac424424a285758e8e3d28ce875524cd820ecd164fa9964563c
3
  size 3554214752
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
- size 11421896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
3
+ size 11422063
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79a6bbc9ef71a3349cad0494254594b09b474e70678cf8ad7d44af9a7a0658cd
3
- size 8440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c5f4167933ef96018db132875272c67911dfa004931d47ad98ef013a7f09d50
3
+ size 8376