GPTQ-for-LLaMa
serge
GPTQ-for-LLaMa | serge | |
---|---|---|
19 | 40 | |
129 | 5,543 | |
- | 0.7% | |
7.7 | 9.8 | |
11 months ago | 1 day ago | |
Python | Svelte | |
- | Apache License 2.0 |
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
serge
- Show HN: I made an app to use local AI as daily driver
- chatgpt alternative
-
Show HN: LlamaGPT – Self-hosted, offline, private AI chatbot, powered by Llama 2
Very cool, this looks like a combination of chatbot-ui and llama-cpp-python? A similar project I've been using is https://github.com/serge-chat/serge. Nous-Hermes-Llama2-13b is my daily driver and scores high on coding evaluations (https://huggingface.co/spaces/mike-ravkine/can-ai-code-resul...).
-
LeCun: Qualcomm working with Meta to run Llama-2 on mobile devices
You might be pleased to hear that nothing really stops you from doing this today. If you ran Serge[0] on a Mac with Tailscale, you could hack together a decently-accelerated Llama chatbot.
[0] https://github.com/serge-chat/serge
-
Chatbot frontend library in Svelte?
Cannot help you with libraries specifically but both Serge and ChatUI are built using SvelteKit, so the code might be of some use to you.
- We’re back and…
-
Best way to use AMD CPU and GPU
Serge made it really easy for me to get started, but it all CPU-based.
-
Need Help
All that said this project probably solves your problem: https://github.com/serge-chat/serge
- Are you selfhosting a ChatGPT alternative?
-
What the hell??
You can play a little bit with more straightforward local models (the simplest to setup is https://github.com/nsarrazin/serge ), to see that any LLM is basically a party trick.
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
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.
llama.cpp - LLM inference in C/C++
GPTQ-for-LLaMa - 4 bits quantization of LLaMA using GPTQ
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
one-click-installers - Simplified installers for oobabooga/text-generation-webui.
FastChat - An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
private-gpt - Interact with your documents using the power of GPT, 100% privately, no data leaks
llama-gpt - A self-hosted, offline, ChatGPT-like chatbot. Powered by Llama 2. 100% private, with no data leaving your device. New: Code Llama support!