I tried to run or download Falcon LLM to my local machine. I got the codes from https://github.com/h2oai/h2ogpt then when I tried to run the script below:
python generate.py --base_model=h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v3 --score_model=None --prompt_type=human_bot --cli=True --load_8bit=True
I keep on getting this error
CUDA SETUP: PyTorch settings found: CUDA_VERSION=117, Highest Compute Capability: 7.5. CUDA SETUP: To manually override the PyTorch CUDA version please see:https://github.com/TimDettmers/bitsandbytes/blob/main/how_to_use_nonpytorch_cuda.md CUDA SETUP: Loading binary C:\Users\BahugBilat\AppData\Local\Programs\Python\Python311\Lib\site-packages\bitsandbytes\libbitsandbytes_cuda117.so... argument of type 'WindowsPath' is not iterable CUDA SETUP: Problem: The main issue seems to be that the main CUDA runtime library was not detected. CUDA SETUP: Solution 1: To solve the issue the libcudart.so location needs to be added to the LD_LIBRARY_PATH variable CUDA SETUP: Solution 1a): Find the cuda runtime library via: find / -name libcudart.so 2>/dev/null CUDA SETUP: Solution 1b): Once the library is found add it to the LD_LIBRARY_PATH: export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:FOUND_PATH_FROM_1a CUDA SETUP: Solution 1c): For a permanent solution add the export from 1b into your .bashrc file, located at ~/.bashrc CUDA SETUP: Solution 2: If no library was found in step 1a) you need to install CUDA. CUDA SETUP: Solution 2a): Download CUDA install script: wget https://github.com/TimDettmers/bitsandbytes/blob/main/cuda_install.sh CUDA SETUP: Solution 2b): Install desired CUDA version to desired location. The syntax is bash cuda_install.sh CUDA_VERSION PATH_TO_INSTALL_INTO. CUDA SETUP: Solution 2b): For example, "bash cuda_install.sh 113 ~/local/" will download CUDA 11.3 and install into the folder ~/local
I have added CUDA to my environment variables as follow: Name: CUDA_PATH, Path: C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.2\bin
But I am still getting the error. How to resolve this error?
I am expecting that the script python generate.py --base_model=h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v3 --score_model=None --prompt_type=human_bot --cli=True --load_8bit=True will work