|
--- |
|
title: README |
|
emoji: 🌍 |
|
colorFrom: gray |
|
colorTo: red |
|
sdk: static |
|
pinned: false |
|
--- |
|
|
|
**Our Github Page**: [https://github.com/Q-Future](https://github.com/Q-Future) |
|
|
|
Please use the HF versions for the benchmark datasets by Q-Future. |
|
|
|
```python |
|
from datasets import load_dataset |
|
|
|
ds = load_dataset("q-future/Q-Bench-HF") # or A-Bench-HF, Q-Bench2-HF |
|
ds["dev"][0] # Containing images (in PIL.ImageFile), questions, and answers |
|
``` |
|
### Our Spaces |
|
|
|
Great thanks to the research GPU grants! |
|
|
|
|
|
- **Q-Align** (*Most Powerful Visual Scorer*): <a href="https://huggingface.co/spaces/teowu/OneScorer"><img src="https://huggingface.co/datasets/huggingface/badges/raw/main/open-in-hf-spaces-lg-dark.svg" alt="Open in Huggingface Spaces"></a> |
|
- **Q-Instruct** (*Low-level Vision-Language Assistant/Chatbot, support 1-4 images*): <a href="https://huggingface.co/spaces/teowu/Q-Instruct-v1"><img src="https://huggingface.co/datasets/huggingface/badges/raw/main/open-in-hf-spaces-lg-dark.svg" alt="Open in Huggingface Spaces"></a> |
|
- **Q-Bench** (*Benchmark for General Purpose MLLMs*): <a href="https://huggingface.co/spaces/Q-Future/Q-Bench-Leaderboard"><img src="https://huggingface.co/datasets/huggingface/badges/raw/main/open-in-hf-spaces-lg-dark.svg" alt="Open in Huggingface Spaces"></a> |
|
|
|
|
|
### Our Mainstream Models |
|
- `q-future/one-align`: AutoModel for Visual Scoring. Trained with Mixture of existing datasets: See [Github](https://github.com/Q-Future/Q-Align) 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**](https://q-future.github.io/Q-Instruct/fig/Q_Instruct_v0_1_preview.pdf). 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.* |
