Video-Text-to-Text
PEFT
Safetensors
caption-evaluation
video-captioning
image-captioning
lora
qwen3-vl
Instructions to use ShuitsuKoyama/Rigel with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use ShuitsuKoyama/Rigel with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
|
Download README.md from ShuitsuKoyama/Rigel: direct link, hf CLI and curl.
- Browser
- Download file 919 Bytes
-
https://huggingface.co/ShuitsuKoyama/Rigel/resolve/main/README.md
- Command line
-
hf download hf://ShuitsuKoyama/Rigel/README.md
-
curl -L -o README.md https://huggingface.co/ShuitsuKoyama/Rigel/resolve/main/README.md
919 Bytes
metadata
license: bsd-3-clause
base_model: Qwen/Qwen3-VL-2B-Instruct
library_name: peft
pipeline_tag: video-text-to-text
tags:
- caption-evaluation
- video-captioning
- image-captioning
- lora
- qwen3-vl
Rigel
Rigel is a caption quality scorer for videos and images. Given a video or image, a candidate caption, and optionally reference captions, it outputs a continuous score in [0, 1].
Usage
git clone https://github.com/SHUonkei/Rigel
cd Rigel
uv sync
uv run rigel-score --media path/to/video.mp4 \
--cand "a man is playing guitar on stage" \
--ref "a musician performs a guitar solo"
from rigel import from_pretrained
model = from_pretrained() # downloads this repository
scores = model(
media_path=["path/to/video.mp4"],
cand=["a man is playing guitar on stage"],
refs=[["a musician performs a guitar solo"]], # [[]] for reference-free scoring
)