Variants of Visual Evaluation Models proposed by [Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-defined Levels]. Use by `model.score()`!
Q-Future
community
AI & ML interests
None defined yet.
Organization Card
About org cards
Our Github Page: https://github.com/Q-Future
Our Spaces
Great thanks to the research GPU grants!
- Q-Align (Most Powerful Visual Scorer):
- Q-Instruct (Low-level Vision-Language Assistant/Chatbot, support 1-4 images):
- Q-Bench (Benchmark for General Purpose MLLMs):
Our Mainstream Models
q-future/one-align
: AutoModel for Visual Scoring. Trained with Mixture of existing datasets: See Github for details.q-future/co-instruct
: AutoModel for Low-level Visual Dialog (Description, Comparison, Question Answering). Trained with the scaled Co-Instruct-562K dataset (will also release soon!).q-future/q-instruct-mplug-owl2-1031
: Older version of Q-Instruct, as reported by paper. Trained with released Q-Instruct-200K dataset.
Though we have other model variants released for the community to replicate our results, please use the previous ones as they are proved to have more stable performance.
models
22
q-future/q-align-only-pair
Text Generation
•
Updated
•
4
q-future/q-align-single-pair
Text Generation
•
Updated
•
4
q-future/t2i-scorer
Text Generation
•
Updated
•
4
q-future/t2i-scorer-ft
Updated
q-future/t2i-scorer-it
Text Generation
•
Updated
•
7
q-future/q-align-sc-itu
Text Generation
•
Updated
•
4
q-future/q-align-sc-fss
Text Generation
•
Updated
•
4
q-future/q-align-ft-ytugc
Feature Extraction
•
Updated
•
2
q-future/co-instruct
Image-Text-to-Text
•
Updated
•
390
•
15
q-future/co-instruct-llava-v1.5-7b
Text Generation
•
Updated
•
3
•
1