LAW1223
LAW1223
目前我們還不支持 MacBook GPU来使用，但我們將會在未來進行探索。請留意我們的進展。謝謝您的關注！ We currently do not support the use of MacBook GPU, but we will explore this possibility in the future. Please stay tuned for updates. Thank you for...
Thank you for your interest in our work! For the first question, we have successfully deployed it on A100, A5000 and V100, but we haven't tried it on other types...
For Bunny-v1.0-3B. It takes about 13 and 12 hours for pretraining and fine-tuning, separately.
The current code version only supports single-image training. The multi-image training and evaluation capabilities will be included in a future release, and the code will be made publicly available at...
进行预训练后，如果想直接评估，可以手动merge一下权重
一般不会更新，因为预训练是为了对齐image encoder 和 llm 的特征
进行预训练后，如果想直接评估，可以手动merge一下权重
Thank you for your excellent work, I have some questions about the dataset. The file structure of CLOTH3D is every .obj is belongs to a fold. In this repo, should...
Thank you for your reply, would using 50 prompts be too little, have you tried increasing the prompts and will it improve performance?