Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
manifestasi
/
RetinaVLM-300M-DPO
like
0
Image-to-Text
Transformers
Safetensors
trl-lib/rlaif-v
English
idefics3
Generated from Trainer
dpo
trl
4-bit precision
bitsandbytes
arxiv:
2305.18290
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
RetinaVLM-300M-DPO
/
chat_template.json
Commit History
Upload folder using huggingface_hub
b887625
verified
manifestasi
commited on
Jul 7