oobabooga / GPTQ-for-LLaMa
4 bits quantization of LLaMa using GPTQ
☆130Updated last year
Alternatives and similar repositories for GPTQ-for-LLaMa:
Users that are interested in GPTQ-for-LLaMa are comparing it to the libraries listed below
- Landmark Attention: Random-Access Infinite Context Length for Transformers QLoRA☆123Updated last year
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆37Updated last year
- 8-bit CUDA functions for PyTorch in Windows 10☆69Updated last year
- Automated prompting and scoring framework to evaluate LLMs using updated human knowledge prompts☆112Updated last year
- Harnessing the Memory Power of the Camelids☆146Updated last year
- 4 bits quantization of LLMs using GPTQ☆49Updated last year
- A gradio web UI for running Large Language Models like GPT-J 6B, OPT, GALACTICA, LLaMA, and Pygmalion.☆310Updated last year
- oobaboga -text-generation-webui implementation of wafflecomposite - langchain-ask-pdf-local☆70Updated last year
- An experimental open-source attempt to make GPT-4 fully autonomous.☆98Updated 2 years ago
- A KoboldAI-like memory extension for oobabooga's text-generation-webui☆109Updated 6 months ago
- Instruct-tune LLaMA on consumer hardware☆74Updated last year
- Just a simple HowTo for https://github.com/johnsmith0031/alpaca_lora_4bit☆31Updated last year
- Text WebUI extension to add clever Notebooks to Chat mode☆139Updated last year
- RWKV is a RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best …☆414Updated last year
- Train llama with lora on one 4090 and merge weight of lora to work as stanford alpaca.☆51Updated last year
- ☆535Updated last year
- The code we currently use to fine-tune models.☆114Updated last year
- Patch for MPT-7B which allows using and training a LoRA☆58Updated last year
- 📖 — Notebooks related to RWKV☆59Updated last year
- ChatGPT-like Web UI for RWKVstic☆100Updated 2 years ago
- 8-bit CUDA functions for PyTorch☆44Updated last year
- ☆156Updated last year
- A finetuning pipeline for instruct tuning Raven 14bn using QLORA 4bit and the Ditty finetuning library☆28Updated 11 months ago
- Load local LLMs effortlessly in a Jupyter notebook for testing purposes alongside Langchain or other agents. Contains Oobagooga and Kobol…☆213Updated last year
- Train Llama Loras Easily☆31Updated last year
- An autonomous AI agent extension for Oobabooga's web ui☆175Updated last year
- Our data munging code.☆34Updated 7 months ago
- Local LLM ReAct Agent with Guidance☆158Updated last year
- Simple and fast server for GPTQ-quantized LLaMA inference☆24Updated last year
- QLoRA: Efficient Finetuning of Quantized LLMs☆78Updated last year