-
-
Save mberman84/9e008131d96af27256cc9cb53ad834cf to your computer and use it in GitHub Desktop.
| # Make sure you have Anaconda installed | |
| # This tutorial assumes you have an Nvidia GPU, but you can find the non-GPU version on the Textgen WebUI github | |
| # More information found here: https://github.com/oobabooga/text-generation-webui | |
| conda create -n textgen python=3.10.9 | |
| conda activate textgen | |
| pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu117 | |
| git clone https://github.com/oobabooga/text-generation-webui | |
| cd text-generation-webui | |
| python -m pip install -r requirements.txt | |
| python -m torch.utils.collect_env # optional, checks that you have CUDA enabled | |
| # if you have trouble with CUDA being enabled in torch, try this: | |
| conda install pytorch torchvision torchaudio pytorch-cuda=11.7 -c pytorch -c nvidia | |
| # if you run into the chardet and cchardet issues I did, try this: | |
| python -m pip install chardet | |
| python -m pip install cchardet | |
| python server.py |
Thanks man
Hi, I am using mac and getting the following error white executing the following line:
(textgen) ~/Documents/test/ pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu117 Looking in indexes: https://download.pytorch.org/whl/cu117 ERROR: Could not find a version that satisfies the requirement torch (from versions: none) ERROR: No matching distribution found for torch
Double check that your installed cuda version matches the torch version you're installing in this environment. @mberman84 installing cu117 but if you have cuda 11.8 use this instead: pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
You can check your cuda version in cmd using: nvcc --version
Finally use suggested code to check that cuda is available: python -m torch.utils.collect_env
Traceback (most recent call last):
File "C:\Users\dell\text-generation-webui\modules\ui_model_menu.py", line 213, in load_model_wrapper
shared.model, shared.tokenizer = load_model(selected_model, loader)
File "C:\Users\dell\text-generation-webui\modules\models.py", line 87, in load_model
output = load_func_maploader
File "C:\Users\dell\text-generation-webui\modules\models.py", line 387, in ExLlamav2_HF_loader
from modules.exllamav2_hf import Exllamav2HF
File "C:\Users\dell\text-generation-webui\modules\exllamav2_hf.py", line 7, in
from exllamav2 import (
File "C:\Users\dell\AppData\Local\Programs\Python\Python310\lib\site-packages\exllamav2_init_.py", line 3, in
from exllamav2.model import ExLlamaV2
File "C:\Users\dell\AppData\Local\Programs\Python\Python310\lib\site-packages\exllamav2\model.py", line 17, in
from exllamav2.cache import ExLlamaV2CacheBase
File "C:\Users\dell\AppData\Local\Programs\Python\Python310\lib\site-packages\exllamav2\cache.py", line 2, in
from exllamav2.ext import exllamav2_ext as ext_c
File "C:\Users\dell\AppData\Local\Programs\Python\Python310\lib\site-packages\exllamav2\ext.py", line 15, in
import exllamav2_ext
ImportError: DLL load failed while importing exllamav2_ext: The specified module could not be found.
How can I resolve this
How can I resolve this
I'm having the same issue
Why don't you read the thread? All of your errors come from the fact that you haven't cloned the exllama repo 1st solution (faster, best etc) : Use Pinokio https://pinokio.computer/ 2nd solution: clone the exllama repo https://github.com/turboderp/exllama into the appropriate folder (READ THE README PLEASE!) https://user-images.githubusercontent.com/70014984/265704342-eb505282-c4b6-498d-8201-82723ed5c939.png
can you tell me where I have to place the repositories folder exactly?
(textgeneration) C:\Users\Patrick>python server.py
python: can't open file 'C:\Users\Patrick\server.py': [Errno 2] No such file or directory
(textgeneration) C:\Users\Patrick\text-generation-webui>python server.py
Traceback (most recent call last):
File "C:\Users\Patrick\text-generation-webui\server.py", line 4, in
from modules import shared
File "C:\Users\Patrick\text-generation-webui\modules\shared.py", line 10, in
from modules.logging_colors import logger
File "C:\Users\Patrick\text-generation-webui\modules\logging_colors.py", line 67, in
setup_logging()
File "C:\Users\Patrick\text-generation-webui\modules\logging_colors.py", line 30, in setup_logging
from rich.console import Console
ModuleNotFoundError: No module named 'rich'
22:29:20-139114 ERROR Failed to load the model.
Traceback (most recent call last):
File "C:\Users\onego\anaconda3\envs\textgen\lib\site-packages\transformers\utils\import_utils.py", line 1364, in get_module
return importlib.import_module("." + module_name, self.name)
File "C:\Users\onego\anaconda3\envs\textgen\lib\importlib_init.py", line 126, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
File "", line 1050, in _gcd_import
File "", line 1027, in _find_and_load
File "", line 1006, in _find_and_load_unlocked
File "", line 688, in _load_unlocked
File "", line 883, in exec_module
File "", line 241, in call_with_frames_removed
File "C:\Users\onego\anaconda3\envs\textgen\lib\site-packages\transformers\models\llama\modeling_llama.py", line 55, in
from flash_attn import flash_attn_func, flash_attn_varlen_func
File "C:\Users\onego\anaconda3\envs\textgen\lib\site-packages\flash_attn_init.py", line 3, in
from flash_attn.flash_attn_interface import (
File "C:\Users\onego\anaconda3\envs\textgen\lib\site-packages\flash_attn\flash_attn_interface.py", line 8, in
import flash_attn_2_cuda as flash_attn_cuda
ImportError: DLL load failed while importing flash_attn_2_cuda: The specified procedure could not be found.
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "C:\Windows\System32\text-generation-webui\modules\ui_model_menu.py", line 220, in load_model_wrapper
shared.model, shared.tokenizer = load_model(selected_model, loader)
File "C:\Windows\System32\text-generation-webui\modules\models.py", line 87, in load_model
output = load_func_maploader
File "C:\Windows\System32\text-generation-webui\modules\models.py", line 235, in huggingface_loader
model = LoaderClass.from_pretrained(path_to_model, **params)
File "C:\Users\onego\anaconda3\envs\textgen\lib\site-packages\transformers\models\auto\auto_factory.py", line 565, in from_pretrained
model_class = _get_model_class(config, cls._model_mapping)
File "C:\Users\onego\anaconda3\envs\textgen\lib\site-packages\transformers\models\auto\auto_factory.py", line 387, in _get_model_class
supported_models = model_mapping[type(config)]
File "C:\Users\onego\anaconda3\envs\textgen\lib\site-packages\transformers\models\auto\auto_factory.py", line 740, in getitem
return self._load_attr_from_module(model_type, model_name)
File "C:\Users\onego\anaconda3\envs\textgen\lib\site-packages\transformers\models\auto\auto_factory.py", line 754, in _load_attr_from_module
return getattribute_from_module(self._modules[module_name], attr)
File "C:\Users\onego\anaconda3\envs\textgen\lib\site-packages\transformers\models\auto\auto_factory.py", line 698, in getattribute_from_module
if hasattr(module, attr):
File "C:\Users\onego\anaconda3\envs\textgen\lib\site-packages\transformers\utils\import_utils.py", line 1354, in getattr
module = self._get_module(self._class_to_module[name])
File "C:\Users\onego\anaconda3\envs\textgen\lib\site-packages\transformers\utils\import_utils.py", line 1366, in _get_module
raise RuntimeError(
RuntimeError: Failed to import transformers.models.llama.modeling_llama because of the following error (look up to see its traceback):
DLL load failed while importing flash_attn_2_cuda: The specified procedure could not be found.
(textgeneration) C:\Users\Patrick>python server.py python: can't open file 'C:\Users\Patrick\server.py': [Errno 2] No such file or directory
this was the cause of the error. conda install pytorch torchvision torchaudio pytorch-cuda=11.7 -c pytorch -c nvidia
please help what is this issue
PS C:\Users\Hp\cChardet> pip install twint
Defaulting to user installation because normal site-packages is not writeable
Collecting twint
Using cached twint-2.1.20-py3-none-any.whl
Requirement already satisfied: aiohttp in c:\users\hp\appdata\local\packages\pythonsoftwarefoundation.python.3.12_qbz5n2kfra8p0\localcache\local-packages\python312\site-packages (from twint) (3.9.3)
Collecting aiodns (from twint)
Using cached aiodns-3.1.1-py3-none-any.whl.metadata (4.0 kB)
Requirement already satisfied: beautifulsoup4 in c:\users\hp\appdata\local\packages\pythonsoftwarefoundation.python.3.12_qbz5n2kfra8p0\localcache\local-packages\python312\site-packages (from twint) (4.12.3)
Collecting cchardet (from twint)
Using cached cchardet-2.1.7.tar.gz (653 kB)
Preparing metadata (setup.py) ... done
Collecting elasticsearch (from twint)
Using cached elasticsearch-8.12.1-py3-none-any.whl.metadata (5.3 kB)
Requirement already satisfied: pysocks in c:\users\hp\appdata\local\packages\pythonsoftwarefoundation.python.3.12_qbz5n2kfra8p0\localcache\local-packages\python312\site-packages (from twint) (1.7.1)
Requirement already satisfied: pandas in c:\users\hp\appdata\local\packages\pythonsoftwarefoundation.python.3.12_qbz5n2kfra8p0\localcache\local-packages\python312\site-packages (from twint) (2.2.1)
Collecting aiohttp-socks (from twint)
Using cached aiohttp_socks-0.8.4-py3-none-any.whl.metadata (3.1 kB)
Collecting schedule (from twint)
Using cached schedule-1.2.1-py2.py3-none-any.whl.metadata (3.3 kB)
Collecting geopy (from twint)
Using cached geopy-2.4.1-py3-none-any.whl.metadata (6.8 kB)
Collecting fake-useragent (from twint)
Using cached fake_useragent-1.4.0-py3-none-any.whl.metadata (13 kB)
Requirement already satisfied: googletransx in c:\users\hp\appdata\local\packages\pythonsoftwarefoundation.python.3.12_qbz5n2kfra8p0\localcache\local-packages\python312\site-packages (from twint) (2.4.2)
Collecting pycares>=4.0.0 (from aiodns->twint)
Using cached pycares-4.4.0-cp312-cp312-win_amd64.whl.metadata (4.5 kB)
Requirement already satisfied: aiosignal>=1.1.2 in c:\users\hp\appdata\local\packages\pythonsoftwarefoundation.python.3.12_qbz5n2kfra8p0\localcache\local-packages\python312\site-packages (from aiohttp->twint) (1.3.1)
Requirement already satisfied: attrs>=17.3.0 in c:\users\hp\appdata\local\packages\pythonsoftwarefoundation.python.3.12_qbz5n2kfra8p0\localcache\local-packages\python312\site-packages (from aiohttp->twint) (23.2.0)
Requirement already satisfied: frozenlist>=1.1.1 in c:\users\hp\appdata\local\packages\pythonsoftwarefoundation.python.3.12_qbz5n2kfra8p0\localcache\local-packages\python312\site-packages (from aiohttp->twint) (1.4.1)
Requirement already satisfied: multidict<7.0,>=4.5 in c:\users\hp\appdata\local\packages\pythonsoftwarefoundation.python.3.12_qbz5n2kfra8p0\localcache\local-packages\python312\site-packages (from aiohttp->twint) (6.0.5)
Requirement already satisfied: yarl<2.0,>=1.0 in c:\users\hp\appdata\local\packages\pythonsoftwarefoundation.python.3.12_qbz5n2kfra8p0\localcache\local-packages\python312\site-packages (from aiohttp->twint) (1.9.4)
Collecting python-socks<3.0.0,>=2.4.3 (from python-socks[asyncio]<3.0.0,>=2.4.3->aiohttp-socks->twint)
Using cached python_socks-2.4.4-py3-none-any.whl.metadata (7.1 kB)
Requirement already satisfied: soupsieve>1.2 in c:\users\hp\appdata\local\packages\pythonsoftwarefoundation.python.3.12_qbz5n2kfra8p0\localcache\local-packages\python312\site-packages (from beautifulsoup4->twint) (2.5)
Collecting elastic-transport<9,>=8 (from elasticsearch->twint)
Using cached elastic_transport-8.12.0-py3-none-any.whl.metadata (3.5 kB)
Collecting geographiclib<3,>=1.52 (from geopy->twint)
Using cached geographiclib-2.0-py3-none-any.whl.metadata (1.4 kB)
Requirement already satisfied: requests in c:\users\hp\appdata\local\packages\pythonsoftwarefoundation.python.3.12_qbz5n2kfra8p0\localcache\local-packages\python312\site-packages (from googletransx->twint) (2.31.0)
Requirement already satisfied: numpy<2,>=1.26.0 in c:\users\hp\appdata\local\packages\pythonsoftwarefoundation.python.3.12_qbz5n2kfra8p0\localcache\local-packages\python312\site-packages (from pandas->twint) (1.26.4)
Requirement already satisfied: python-dateutil>=2.8.2 in c:\users\hp\appdata\local\packages\pythonsoftwarefoundation.python.3.12_qbz5n2kfra8p0\localcache\local-packages\python312\site-packages (from pandas->twint) (2.8.2)
Requirement already satisfied: pytz>=2020.1 in c:\users\hp\appdata\local\packages\pythonsoftwarefoundation.python.3.12_qbz5n2kfra8p0\localcache\local-packages\python312\site-packages (from pandas->twint) (2024.1)
Requirement already satisfied: tzdata>=2022.7 in c:\users\hp\appdata\local\packages\pythonsoftwarefoundation.python.3.12_qbz5n2kfra8p0\localcache\local-packages\python312\site-packages (from pandas->twint) (2024.1)
Requirement already satisfied: urllib3<3,>=1.26.2 in c:\users\hp\appdata\local\packages\pythonsoftwarefoundation.python.3.12_qbz5n2kfra8p0\localcache\local-packages\python312\site-packages (from elastic-transport<9,>=8->elasticsearch->twint) (2.2.1)
Requirement already satisfied: certifi in c:\users\hp\appdata\local\packages\pythonsoftwarefoundation.python.3.12_qbz5n2kfra8p0\localcache\local-packages\python312\site-packages (from elastic-transport<9,>=8->elasticsearch->twint) (2024.2.2)
Collecting cffi>=1.5.0 (from pycares>=4.0.0->aiodns->twint)
Using cached cffi-1.16.0-cp312-cp312-win_amd64.whl.metadata (1.5 kB)
Requirement already satisfied: six>=1.5 in c:\users\hp\appdata\local\packages\pythonsoftwarefoundation.python.3.12_qbz5n2kfra8p0\localcache\local-packages\python312\site-packages (from python-dateutil>=2.8.2->pandas->twint) (1.16.0)
Collecting async-timeout>=3.0.1 (from python-socks[asyncio]<3.0.0,>=2.4.3->aiohttp-socks->twint)
Using cached async_timeout-4.0.3-py3-none-any.whl.metadata (4.2 kB)
Requirement already satisfied: idna>=2.0 in c:\users\hp\appdata\local\packages\pythonsoftwarefoundation.python.3.12_qbz5n2kfra8p0\localcache\local-packages\python312\site-packages (from yarl<2.0,>=1.0->aiohttp->twint) (3.6)
Requirement already satisfied: charset-normalizer<4,>=2 in c:\users\hp\appdata\local\packages\pythonsoftwarefoundation.python.3.12_qbz5n2kfra8p0\localcache\local-packages\python312\site-packages (from requests->googletransx->twint) (3.3.2)
Collecting pycparser (from cffi>=1.5.0->pycares>=4.0.0->aiodns->twint)
Using cached pycparser-2.21-py2.py3-none-any.whl.metadata (1.1 kB)
Using cached aiodns-3.1.1-py3-none-any.whl (5.4 kB)
Using cached aiohttp_socks-0.8.4-py3-none-any.whl (9.6 kB)
Using cached elasticsearch-8.12.1-py3-none-any.whl (432 kB)
Using cached fake_useragent-1.4.0-py3-none-any.whl (15 kB)
Using cached geopy-2.4.1-py3-none-any.whl (125 kB)
Using cached schedule-1.2.1-py2.py3-none-any.whl (11 kB)
Using cached elastic_transport-8.12.0-py3-none-any.whl (59 kB)
Using cached geographiclib-2.0-py3-none-any.whl (40 kB)
Using cached pycares-4.4.0-cp312-cp312-win_amd64.whl (76 kB)
Using cached python_socks-2.4.4-py3-none-any.whl (52 kB)
Using cached async_timeout-4.0.3-py3-none-any.whl (5.7 kB)
Using cached cffi-1.16.0-cp312-cp312-win_amd64.whl (181 kB)
Using cached pycparser-2.21-py2.py3-none-any.whl (118 kB)
Building wheels for collected packages: cchardet
Building wheel for cchardet (setup.py) ... error
error: subprocess-exited-with-error
× python setup.py bdist_wheel did not run successfully.
│ exit code: 1
╰─> [11 lines of output]
running bdist_wheel
running build
running build_py
creating build
creating build\lib.win-amd64-cpython-312
creating build\lib.win-amd64-cpython-312\cchardet
copying src\cchardet\version.py -> build\lib.win-amd64-cpython-312\cchardet
copying src\cchardet_init_.py -> build\lib.win-amd64-cpython-312\cchardet
running build_ext
building 'cchardet._cchardet' extension
error: Microsoft Visual C++ 14.0 or greater is required. Get it with "Microsoft C++ Build Tools": https://visualstudio.microsoft.com/visual-cpp-build-tools/
[end of output]
note: This error originates from a subprocess, and is likely not a problem with pip.
ERROR: Failed building wheel for cchardet
Running setup.py clean for cchardet
Failed to build cchardet
ERROR: Could not build wheels for cchardet, which is required to install pyproject.toml-based projects
PS C:\Users\Hp\cChardet>
Here is the repo that you paste into the Pinokio app to run the full installation - to get Code Llama running, with the web UI:
https://github.com/cocktailpeanut/text-generation-webui.pinokio
FYI: Pinokio views this repo as an "installer" and will perform all of the necessary setup steps for you, automagically (including creating virtual environment, package installations, etc). Once the installation is complete, it lets you launch the "app" through it's UI.
I had not heard about Pinokio until now, and I ran into similar issues with the llama model/cpps, and cuda as well.
It saved me a lot of headeache!