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
2dc8811
·
verified ·
1 Parent(s): 2742f52

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 sha256:85482f6dc8bba12b62e30db3e3f6295bb681913edde8d742b72e3d01fede761b
3
  size 4063515640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdbf6bed99ba3d20f92a02bb10b702b023aa912c21175a4d5ced73e2a1d3e025
3
  size 4063515640
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2f04bdfa7889148e38f02e1ac42c7dc51300a816a08c6492999f8149ad2bfaa
3
  size 7864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78f47c4d89db5096d662a62c061fbc764680aad9e74cbf6631a1bf13b9b5d756
3
  size 7864