Bitsandbytes gives error while -- Initialization of a tokenizer for the Mistral-7b model

[flysaurus]

System Info

Windows 10, Python 3.9.4, GPU Geforce RTX 2060

Reproduction

import os
import torch

General packages

import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
from textwrap import fill
from IPython.display import Markdown, display # for formating Python display folowing markdown language
import warnings
warnings.filterwarnings('ignore') # avoid warning messages importing packages

Mistral and LangChain packages (prompt engineering)

import torch
from langchain import PromptTemplate, HuggingFacePipeline
from langchain.output_parsers import ResponseSchema, StructuredOutputParser
from transformers import BitsAndBytesConfig, AutoModelForCausalLM, AutoTokenizer, GenerationConfig, pipeline

Model version of Mistral

MODEL_NAME = "mistralai/Mistral-7B-Instruct-v0.1"

quantization_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_compute_dtype=torch.float16,
bnb_4bit_quant_type="nf4",
bnb_4bit_use_double_quant=True,
)

################### BELOW CELL ERRORS OUT #######################

Initialization of a tokenizer for the Mistral-7b model,

necessary to preprocess text data for input

tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, use_fast=True)
tokenizer.pad_token = tokenizer.eos_token

Initialization of the pre-trained language Mistral-7b

model = AutoModelForCausalLM.from_pretrained(
MODEL_NAME, torch_dtype=torch.float16,
trust_remote_code=True,
device_map="auto",
quantization_config=quantization_config
)

################### ERROR OUTPUT #############################
False

===================================BUG REPORT===================================

The following directories listed in your path were found to be non-existent: {WindowsPath('/matplotlib_inline.backend_inline'), WindowsPath('module')}
The following directories listed in your path were found to be non-existent: {WindowsPath('vs/workbench/api/node/extensionHostProcess')}
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=121, 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 f:\0.MilindPython\Mistral.venv\lib\site-packages\bitsandbytes\libbitsandbytes_cuda121.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
f:\0.MilindPython\Mistral.venv\lib\site-packages\bitsandbytes\cuda_setup\main.py:167: UserWarning: Welcome to bitsandbytes. For bug reports, please run

python -m bitsandbytes

warn(msg)
Traceback (most recent call last):
File "C:\Python39\lib\runpy.py", line 188, in _run_module_as_main
mod_name, mod_spec, code = _get_module_details(mod_name, Error)
File "C:\Python39\lib\runpy.py", line 147, in get_module_details
return get_module_details(pkg_main_name, error)
File "C:\Python39\lib\runpy.py", line 111, in get_module_details
import(pkg_name)
File "f:\0.MilindPython\Mistral.venv\lib\site-packages\bitsandbytes_init.py", line 6, in
from . import cuda_setup, utils, research
File "f:\0.MilindPython\Mistral.venv\lib\site-packages\bitsandbytes\research_init.py", line 1, in
from . import nn
File "f:\0.MilindPython\Mistral.venv\lib\site-packages\bitsandbytes\research\nn_init.py", line 1, in
from .modules import LinearFP8Mixed, LinearFP8Global
File "f:\0.MilindPython\Mistral.venv\lib\site-packages\bitsandbytes\research\nn\modules.py", line 8, in
from bitsandbytes.optim import GlobalOptimManager
File "f:\0.MilindPython\Mistral.venv\lib\site-packages\bitsandbytes\optim_init.py", line 6, in
from bitsandbytes.cextension import COMPILED_WITH_CUDA
File "f:\0.MilindPython\Mistral.venv\lib\site-packages\bitsandbytes\cextension.py", line 20, in
raise RuntimeError('''
RuntimeError:
CUDA Setup failed despite GPU being available. Please run the following command to get more information:

    python -m bitsandbytes

    Inspect the output of the command and see if you can locate CUDA libraries. You might need to add them
    to your LD_LIBRARY_PATH. If you suspect a bug, please take the information from python -m bitsandbytes
    and open an issue at: https://github.com/TimDettmers/bitsandbytes/issues

python -m bitsandbytes RETURNS THE SAME ABOVE OUTPUT

Expected behavior

Tokenizer initialized

[Titus-von-Koeller]

Hey @flysaurus Thanks for raising this.

Unfortunately, we don't provide official Windows support yet. Though there is an unofficial Windows fork and we're working to integrate it in our current cross-platform effort. The official support might still take a while though.

We need to add to the documentation a disclaimer that Windows or Mac is not supported.

Where would you think that would be best placed other than our own docs? Probably in the HF docs and when a mention in the issue template would be good.

[Titus-von-Koeller]

@wkpark Do you think there is an easy way to add an descriptive error in setup.py when detecting Windows?

[wkpark]

@wkpark Do you think there is an easy way to add an descriptive error in setup.py when detecting Windows?

the current wheel file is "bitsandbytes-0.42.0-py3-none-any.whl" so any platform can install it, (in cmake PR, add ext_modules=[Extension("bitsandbytes", sources=[], language="c")], option to setup() call will make platform dependent wheel. 9d65351#diff-60f61ab7a8d1910d86d9fda2261620314edcae5894d5aaa236b821c7256badd7R39 as bitsandbytes-0.42.0-cp310-cp310-win_amd64.whl

(Please see also #876 (this is a minimal windows fix))

and, current main branch has dll lib detection for windows, the following warning message will be printed

>python -m bitsandbytes
False

===================================BUG REPORT===================================
F:\webui\webui\stable-diffusion-webui\venv\lib\site-packages\bitsandbytes\cuda_setup\main.py:177: UserWarning: Welcome to bitsandbytes. For bug reports, please run

python -m bitsandbytes


  warn(msg)
================================================================================
The following directories listed in your path were found to be non-existent: {WindowsPath('F:/CUDA/v10.0')}
The following directories listed in your path were found to be non-existent: {WindowsPath('F:/CUDA/v8.0')}
The following directories listed in your path were found to be non-existent: {WindowsPath('F:/CUDA/v9.0')}
The following directories listed in your path were found to be non-existent: {WindowsPath('F:/CUDA/v9.2')}
The following directories listed in your path were found to be non-existent: {WindowsPath('/Users/WK')}
The following directories listed in your path were found to be non-existent: {WindowsPath('/DESKTOP-HEAVEN')}
The following directories listed in your path were found to be non-existent: {WindowsPath('F:/CUDA/v8.0')}
The following directories listed in your path were found to be non-existent: {WindowsPath('F:/CUDA/v9.0')}
The following directories listed in your path were found to be non-existent: {WindowsPath('F:/OpenSSL-Win64/bin/openssl.cfg')}
The following directories listed in your path were found to be non-existent: {WindowsPath('10.0.20348.0')}
The following directories listed in your path were found to be non-existent: {WindowsPath('10.0.20348.0')}
The following directories listed in your path were found to be non-existent: {WindowsPath('C:/Users/WK/go/bin'), WindowsPath('C:/Users/WK/mambaforge/Library/usr/bin'), WindowsPath('F:/CUDA/v9.0/libnvvp'), WindowsPath('C:/Program Files (x86)/Microsoft SDKs/TypeScript/1.0'), WindowsPath('C:/Program Files (x86)/ePapyrus/Papyrus-PlugIn-web'), WindowsPath('F:/CUDA/v10.0/bin'), WindowsPath('F:/CUDA/nasm-2.13.01'), WindowsPath('C:/Users/WK/AppData/Roaming/npm'), WindowsPath('C:/Program Files (x86)/ePapyrus/Papyrus-PlugIn-web/Addins'), WindowsPath('C:/Program Files (x86)/AMD/ATI.ACE/Core-Static'), WindowsPath('F:/CUDA/v9.0/bin'), WindowsPath('C:/Users/WK/mambaforge/Library/mingw-w64/bin'), WindowsPath('F:/CUDA/v10.0/libnvvp')}
The following directories listed in your path were found to be non-existent: {WindowsPath('C:/Users/WK/go/bin'), WindowsPath('C:/Users/WK/mambaforge/Library/usr/bin'), WindowsPath('F:/CUDA/v9.0/libnvvp'), WindowsPath('C:/Program Files (x86)/Microsoft SDKs/TypeScript/1.0'), WindowsPath('C:/Program Files (x86)/ePapyrus/Papyrus-PlugIn-web'), WindowsPath('F:/CUDA/v10.0/bin'), WindowsPath('F:/CUDA/nasm-2.13.01'), WindowsPath('C:/Users/WK/AppData/Roaming/npm'), WindowsPath('C:/Program Files (x86)/ePapyrus/Papyrus-PlugIn-web/Addins'), WindowsPath('C:/Program Files (x86)/AMD/ATI.ACE/Core-Static'), WindowsPath('F:/CUDA/v9.0/bin'), WindowsPath('C:/Users/WK/mambaforge/Library/mingw-w64/bin'), WindowsPath('F:/CUDA/v10.0/libnvvp')}
The following directories listed in your path were found to be non-existent: {WindowsPath('C:/Users/WK/AppData/Local/Packages/PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0/LocalCache/local-packages')}
DEBUG: Possible options found for libcudart.so: {WindowsPath('C:/WINDOWS/system32/nvcuda.dll')}
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: Required library version not found: libbitsandbytes_cuda118.dll. Maybe you need to compile it from source?
CUDA SETUP: Defaulting to libbitsandbytes_cpu.dll...

================================================ERROR=====================================
CUDA SETUP: CUDA detection failed! Possible reasons:
1. You need to manually override the PyTorch CUDA version. Please see: "https://github.com/TimDettmers/bitsandbytes/blob/main/how_to_use_nonpytorch_cuda.md
2. CUDA driver not installed
3. CUDA not installed
4. You have multiple conflicting CUDA libraries
5. Required library not pre-compiled for this bitsandbytes release!
CUDA SETUP: If you compiled from source, try again with `make CUDA_VERSION=DETECTED_CUDA_VERSION` for example, `make CUDA_VERSION=113`.
CUDA SETUP: The CUDA version for the compile might depend on your conda install. Inspect CUDA version via `conda list | grep cuda`.
================================================================================

CUDA SETUP: Something unexpected happened. Please compile from source:
git clone https://github.com/TimDettmers/bitsandbytes.git
cd bitsandbytes
CUDA_VERSION=118 make cuda11x
python setup.py install
CUDA SETUP: Setup Failed!
Traceback (most recent call last):
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.10_3.10.3056.0_x64__qbz5n2kfra8p0\lib\runpy.py", line 187, in _run_module_as_main
    mod_name, mod_spec, code = _get_module_details(mod_name, _Error)
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.10_3.10.3056.0_x64__qbz5n2kfra8p0\lib\runpy.py", line 146, in _get_module_details
    return _get_module_details(pkg_main_name, error)
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.10_3.10.3056.0_x64__qbz5n2kfra8p0\lib\runpy.py", line 110, in _get_module_details
    __import__(pkg_name)
  File "F:\webui\webui\stable-diffusion-webui\venv\lib\site-packages\bitsandbytes\__init__.py", line 6, in <module>
    from . import cuda_setup, utils, research
  File "F:\webui\webui\stable-diffusion-webui\venv\lib\site-packages\bitsandbytes\research\__init__.py", line 1, in <module>
    from . import nn
  File "F:\webui\webui\stable-diffusion-webui\venv\lib\site-packages\bitsandbytes\research\nn\__init__.py", line 1, in <module>
    from .modules import LinearFP8Mixed, LinearFP8Global
  File "F:\webui\webui\stable-diffusion-webui\venv\lib\site-packages\bitsandbytes\research\nn\modules.py", line 8, in <module>
    from bitsandbytes.optim import GlobalOptimManager
  File "F:\webui\webui\stable-diffusion-webui\venv\lib\site-packages\bitsandbytes\optim\__init__.py", line 6, in <module>
    from bitsandbytes.cextension import COMPILED_WITH_CUDA
  File "F:\webui\webui\stable-diffusion-webui\venv\lib\site-packages\bitsandbytes\cextension.py", line 20, in <module>
    raise RuntimeError('''
RuntimeError:
        CUDA Setup failed despite GPU being available. Please run the following command to get more information:

        python -m bitsandbytes

        Inspect the output of the command and see if you can locate CUDA libraries. You might need to add them
        to your LD_LIBRARY_PATH. If you suspect a bug, please take the information from python -m bitsandbytes
        and open an issue at: https://github.com/TimDettmers/bitsandbytes/issues