Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
TMLR-Group-HF
/
GT-Qwen3-4B-Base-OpenRS
like
0
Follow
TMLR Group
20
Text Generation
Transformers
Safetensors
TMLR-Group-HF/Co-rewarding-RephrasedOpenRS
qwen3
qwen
reasoning
self-supervised-learning
reinforcement-learning
conversational
text-generation-inference
arxiv:
2508.00410
License:
mit
Model card
Files
Files and versions
xet
Community
1
Deploy
Use this model
main
GT-Qwen3-4B-Base-OpenRS
/
generation_config.json
resistz
Upload folder using huggingface_hub
dbf6c75
verified
5 months ago
raw
Copy download link
history
blame
contribute
delete
Safe
117 Bytes
{
"bos_token_id"
:
151643
,
"eos_token_id"
:
151643
,
"max_new_tokens"
:
2048
,
"transformers_version"
:
"4.55.4"
}