|
--- |
|
license: other |
|
--- |
|
# Model Card for llava-polyglot-ko-1.3b-hf |
|
|
|
## Model Description |
|
|
|
` llava-polyglot-ko-1.3b-hf ` is a model based on polyglot-ko-13b. |
|
We use llava for the vision question answering. |
|
You can see [‘demo.py’]( https://github.com/LearnItAnyway/llava_gpt_neox/blob/main/demo.py) and [‘llava_gpt_neox.py’]( https://github.com/LearnItAnyway/llava_gpt_neox/blob/main/llava_gpt_neox.py). |
|
Currently, the model has been trained on small vision question answer dataset (approx, 10k) with 1.3b (small) model. |
|
|
|
## TODO |
|
- Multi-turn chat based on the image |
|
- Larger LLM |
|
- More pretraining on for the vision-text adapter |
|
|
|
## References |
|
- [`LLaVA`](https://github.com/haotian-liu/LLaVA) |
|
- [`polyglot korean`](https://huggingface.co/EleutherAI/polyglot-ko-1.3b) |
|
|
|
|