Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
Accio-Lab
/
Metis-8B-RL
like
1
Follow
Accio
2
Image-Text-to-Text
Transformers
Safetensors
Accio-Lab/Metis-RL
English
qwen3_vl
multimodal
vision-language
reinforcement-learning
tool-use
agentic
HDPO
conversational
arxiv:
2604.08545
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
Metis-8B-RL
/
video_preprocessor_config.json
Commit History
Add model files from Occam-8B-RL
db903f1
verified
shilinyan
commited on
4 days ago