Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
knoveleng
/
OpenRS-GRPO
like
5
Follow
Knovel Engineering
30
Text Generation
Safetensors
knoveleng/open-rs
knoveleng/open-s1
knoveleng/open-deepscaler
qwen2
conversational
arxiv:
2503.16219
License:
mit
Model card
Files
Files and versions
Community
1
refs/pr/1
OpenRS-GRPO
/
generation_config.json
quyanh
Upload model for experiment 3, step 50
1793695
verified
3 months ago
raw
Copy download link
history
blame
Safe
181 Bytes
{
"_from_model_config"
:
true
,
"bos_token_id"
:
151646
,
"do_sample"
:
true
,
"eos_token_id"
:
151643
,
"temperature"
:
0.6
,
"top_p"
:
0.95
,
"transformers_version"
:
"4.49.0"
}