GPTQ-for-LLaMa
one-click-installers
GPTQ-for-LLaMa | one-click-installers | |
---|---|---|
19 | 18 | |
129 | 470 | |
- | - | |
7.7 | 8.9 | |
11 months ago | 7 months ago | |
Python | Python | |
- | GNU Affero General Public License v3.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
GPTQ-for-LLaMa
-
I have tried various different methods to install, and none work. Can you spoon-feed me how?
git clone https://github.com/oobabooga/GPTQ-for-LLaMa
-
Query output random text
If you're using the model directly from ehartford, that one hasn't been quantized. Try using the GPTQ quantized version here, and use this fork of GPTQ-for-LLaMa. Load in 4-bit with --wbits 4
-
Help needed with installing quant_cuda for the WebUI
This worked for me on Ubuntu. If you want to use the CUDA branch instead of triton, do the same steps except clone this GPTQ-for-LLaMa fork and run python setup_cuda.py install
-
AutoGPTQ vs GPTQ-for-llama?
If you don't have triton and you use AutoGPTQ you're gonna notice a huge slow down compared to the old GPTQ-for-LLaMA cuda branch. For me AutoGPTQ gives me a whopping 1 token per second compared to the old GPTQ that gives me a decent 9 tokens per second.. both times I used a same sized model. (I think the slowdown is due to AutoGPTQ using the newer cuda branch which is much slower than the old one)
-
Guanaco 7B, 13B, 33B and 65B models by Tim Dettmers: now for your local LLM pleasure
Are you using a later version of GPTQ-for-LLaMa? If so, go to ooba's CUDA fork (https://github.com/oobabooga/GPTQ-for-LLaMa). That's what I made it in and it definitely works with that. And that's what's included in the one-click-installers.
-
Any idea Vicuna 13B 4bit model output random content?
This usually happens when using models that conflict with your GPTQ installation. You should be using this fork: https://github.com/oobabooga/GPTQ-for-LLaMa. If you did the manual installation wrong, use the one click installer instead.
-
GPT4All: A little helper to get started
cd text-generation-webui # wherever you have it installed mkdir -p repositories cd repositories git clone https://github.com/oobabooga/GPTQ-for-LLaMa -b cuda GPTQ-for-LLaMa cd GPTQ-for-LLaMa python setup_cuda install
- wizard-vicuna-13B • Hugging Face
-
Anyone actually running 30b/65b at reasonably high speed? What's your rig?
I'm on GPTQ for LLaMA folder under repositories says it's pointed at https://github.com/oobabooga/GPTQ-for-LLaMa.git. But I've run through the instructions and also applied the monkey patch to train and apply 4 bit lora which may come into play. No idea.
-
Trying to run TheBloke/vicuna-13B-1.1-GPTQ-4bit-128g with latest GPTQ-for-LLaMa CUDA branch
git clone https://github.com/oobabooga/GPTQ-for-LLaMa.git -b cuda
one-click-installers
-
amd gpus on windows support?
AMD does not offer installation options for ROCm on Windows. I'm not familiar with the workarounds to make it work; if you find a solution, you can contribute it to https://github.com/oobabooga/one-click-installers/
-
Oobabooga for Windows
Running start_windows.bat should take care of everything.
-
Quant-Cude Error?
Had the same issue, turns out I was using an old 1 click installer / updater, you need to use https://github.com/oobabooga/one-click-installers and reinstall everything from scratch
-
Cant find the "start: file.
Are you sure you're looking at the right folder? start_windows.bat is there. It's listed in the source code: https://github.com/oobabooga/one-click-installers
- Any UI that allows Windows + AMD GPU ?
- WizardLM-30B-Uncensored
-
13b-4bit-128g - Trying to run compressed model without success. ( problem exist only with 13b models for some reason ) No error code has been displayed.
one-click-installers/INSTRUCTIONS.TXT
-
GPT4All: A little helper to get started
https://github.com/oobabooga/one-click-installers/issues/56 they explain it over here.
-
Visual Studio compile errors
I solved this by adding the Individual components 2019 Windows 10 SDK, C++ CMake tools for Windows, and MSVC v142 - VS 2019 C++ build tools. See https://github.com/oobabooga/one-click-installers/issues/56
-
python setup.py bdist_wheel did not run successfully.
It appears one of the extensions isn't pre-compiled on install. I believe you have the same problem as listed here. https://github.com/oobabooga/one-click-installers/issues/56
What are some alternatives?
exllama - A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.
gpt4all - gpt4all: run open-source LLMs anywhere
koboldcpp - A simple one-file way to run various GGML and GGUF models with KoboldAI's UI
gradio - Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!
langflow - ⛓️ Langflow is a dynamic graph where each node is an executable unit. Its modular and interactive design fosters rapid experimentation and prototyping, pushing hard on the limits of creativity.
KoboldAI
GPTQ-for-LLaMa - 4 bits quantization of LLaMA using GPTQ
WizardVicunaLM - LLM that combines the principles of wizardLM and vicunaLM
private-gpt - Interact with your documents using the power of GPT, 100% privately, no data leaks
micromamba-releases - Micromamba executables mirrored from conda-forge as Github releases
SillyTavern - LLM Frontend for Power Users.
Llama-X - Open Academic Research on Improving LLaMA to SOTA LLM