Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
launch
/
ThinkPRM-14B
like
3
Follow
LAUNCH Lab
26
Text Generation
Transformers
Safetensors
qwen2
reward-model
prm
generative reward model
process supervision
chain-of-thought
verification
math reasoning
code verification
conversational
text-generation-inference
arxiv:
2504.16828
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
2
Train
Deploy
Use this model
refs/pr/2
ThinkPRM-14B
/
generation_config.json
mkhalifa
Upload Qwen2ForCausalLM
6da9919
verified
4 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"
:
"4.48.3"
}