photomz/babydoctor

The AI Radiologist You Can Chat With

babydoctor's Issues

The llava llama2 7b chat model for finetuning is not available

When did you clone our code?

I cloned the code base after 5/1/23

Describe the issue

Hi, I find the link you provided for llava-llama2-77b-chat-finetuning is not available. Could you please kindly update the link for the model? (https://huggingface.co/kaelee/llava-llama-2-7b-chat-finetuning)

Btw, I am wondering what is the difference between the llava-llama-2-7b-chat-finetuning model and the original llava-llama-2-7b-chat model. Thanks!

app build issue with cuda and conda

Question

thanks for sharing this project, I am trying to build this project and its completed till the below commant.
Run conda env create -f BabyDoctor/llmenv.yaml

after that "conda activate llmforbio" is throwing error like llmforbio env not available, actually its not creating this env, chceked in conda path as well.

Then this part of the comment also failed with :
Run MAX_JOBS=8 python3 -m pip install flash-attn

error like :
Using cached flash_attn-1.0.5.tar.gz (2.0 MB)
Installing build dependencies ... done
Getting requirements to build wheel ... error
error: subprocess-exited-with-error

× Getting requirements to build wheel did not run successfully.
│ exit code: 1
╰─> [39 lines of output]
No CUDA runtime is found, using CUDA_HOME='/usr/lib/nvidia-cuda-toolkit/bin'

actually its running and can see the versions 11.5

so Is that possible to provide pip install requirements.txt version to build this ?
also what version of cuda are you using? if possible please provide detailed step instruction.