ningshanwutuobang issues

Repositories
Issues
Comments

Results 2 issues of


                                            ningshanwutuobang

Support input float tensor directly

Add new interface `llama_eval_float` to solve #1552 with examples of using it for [LLaVA](https://github.com/haotian-liu/LLaVA/) model.

[Question] PandaGPT with llama.cpp

I have tried to use [llama.cpp](https://github.com/ggerganov/llama.cpp) for PandaGPT in [panda_gpt_llama_cpp](https://huggingface.co/spaces/ningshanwutuobang/panda_gpt_llama_cpp). The script get poor performance. Is there any thing wrong for the procedure? Or is it just the limit of...