Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
chamber111
/
VPPO-32B
like
2
Safetensors
chamber111/VPPO_ViRL39K_train
qwen2_5_vl
multimodal
visual-reasoning
mathematics
logic
qwen
vppo
arxiv:
2510.09285
License:
mit
Model card
Files
Files and versions
xet
Community
main
VPPO-32B
/
generation_config.json
chamber111
Upload folder using huggingface_hub
b48332a
verified
3 months ago
raw
Copy download link
history
blame
contribute
delete
Safe
121 Bytes
{
"_from_model_config"
:
true
,
"eos_token_id"
:
151645
,
"pad_token_id"
:
151643
,
"transformers_version"
:
"4.52.4"
}