mistralai

/

Mixtral-8x7B-Instruct-v0.1

like 3.89k

I am trying to run Mixtral on my local machine with 64gb ram and a 4090. I use this minimal example:

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2", load_in_4bit=True)
tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2")

messages = [
    {"role": "user", "content": "Sprichst Du auch deutsch?"}
]

inputs = tokenizer(messages, return_tensors="pt").to(0)

outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

But get the following cuda warning (Other llms run with cuda )

CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching in backup paths...
The following directories listed in your path were found to be non-existent: {WindowsPath('/usr/local/cuda/lib64')}
DEBUG: Possible options found for libcudart.so: set()
CUDA SETUP: PyTorch settings found: CUDA_VERSION=118, Highest Compute Capability: 8.9.
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...\venv...\lib\site-packages\bitsandbytes\libbitsandbytes_cuda118.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://raw.githubusercontent.com/TimDettmers/bitsandbytes/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