README.md

metadata

{}

ubitus-llava-13b-ge-v1.0

This model is a fine-tuned version of liuhaotian/llava-v1.5-13b. We have fine-tuned the LLaVA model using screenshots from games. This fine-tuning process enables LLaVA to accurately identify objects and characters within game scenes and provide precise descriptions of those scenes.

Model state

ubitus-llava-13b-ge-v1.0 was trained in January 2024

Framework versions

• Transformers 4.31.0
• Pytorch 2.2.2
• Tokenizers 0.13.3