Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
kevinpro
/
R-PRM-7B-DPO
like
0
Text Generation
Safetensors
Chinese
qwen2
reinforcement-learning
reward-model
dpo
conversational
arxiv:
2503.21295
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
4863973
R-PRM-7B-DPO
/
generation_config.json
kevinpro
Upload folder using huggingface_hub
a4bfcc4
verified
8 months ago
raw
Copy download link
history
blame
Safe
139 Bytes
{
"bos_token_id"
:
151643
,
"eos_token_id"
:
[
151645
,
151643
]
,
"pad_token_id"
:
151643
,
"transformers_version"
:
"4.47.1"
}