oobabooga's starred repositories

open-interpreter

A natural language interface for computers

Language:PythonLicense:AGPL-3.0Stargazers:42175Issues:317Issues:747

TTS

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Language:PythonLicense:MPL-2.0Stargazers:29015Issues:256Issues:1008

llamafile

Distribute and run LLMs with a single file.

Language:C++License:NOASSERTIONStargazers:13415Issues:125Issues:282

flash-attention

Fast and memory-efficient exact attention

Language:PythonLicense:BSD-3-ClauseStargazers:10695Issues:104Issues:776

axolotl

Go ahead and axolotl questions

Language:PythonLicense:Apache-2.0Stargazers:5595Issues:47Issues:520

mergekit

Tools for merging pretrained large language models.

Language:PythonLicense:LGPL-3.0Stargazers:3285Issues:39Issues:183

AutoAWQ

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

Language:PythonLicense:MITStargazers:1169Issues:11Issues:279

Local-LLM-Comparison-Colab-UI

Compare the performance of different LLM that can be deployed locally on consumer hardware. Run yourself with Colab WebUI.

Language:Jupyter NotebookStargazers:855Issues:26Issues:10

evalplus

EvalPlus for rigourous evaluation of LLM-synthesized code

Language:PythonLicense:Apache-2.0Stargazers:853Issues:11Issues:105

AQLM

Official Pytorch repository for Extreme Compression of Large Language Models via Additive Quantization https://arxiv.org/pdf/2401.06118.pdf

Language:PythonLicense:Apache-2.0Stargazers:795Issues:16Issues:39
Language:PythonLicense:GPL-3.0Stargazers:415Issues:10Issues:41

hqq

Official implementation of Half-Quadratic Quantization (HQQ)

Language:PythonLicense:Apache-2.0Stargazers:394Issues:12Issues:39

llama2.py

Inference Llama 2 in one file of pure Python

Language:PythonLicense:MITStargazers:380Issues:4Issues:0

alltalk_tts

AllTalk is based on the Coqui TTS engine, similar to the Coqui_tts extension for Text generation webUI, however supports a variety of advanced features, such as a settings page, low VRAM support, DeepSpeed, narrator, model finetuning, custom models, wav file maintenance. It can also be used with 3rd Party software via JSON calls.

Language:PythonLicense:AGPL-3.0Stargazers:316Issues:9Issues:105

mauve

Package to compute Mauve, a similarity score between neural text and human text. Install with `pip install mauve-text`.

Language:PythonLicense:NOASSERTIONStargazers:259Issues:4Issues:12

BlockMerge_Gradient

Merge Transformers language models by use of gradient parameters.

Language:PythonLicense:Apache-2.0Stargazers:174Issues:3Issues:3

Memoir

Memoir+ a persona extension for Text Gen Web UI. That includes memory, emotions, command handling and more.

Language:PythonLicense:MITStargazers:109Issues:6Issues:24
Language:PythonLicense:Apache-2.0Stargazers:108Issues:5Issues:9

LucidWebSearch

A web search extension for Oobabooga's text-generation-webui (now with nougat)

Language:PythonLicense:AGPL-3.0Stargazers:54Issues:2Issues:8

transformers-CFG

🤗 A specialized library for integrating context-free grammars (CFG) in EBNF with the Hugging Face Transformers

Language:PythonLicense:MITStargazers:47Issues:3Issues:7

chatbot_clinic

Science-driven chatbot development

Language:PythonLicense:AGPL-3.0Stargazers:45Issues:3Issues:13

text-generation-webui-stable_diffusion

Integrate image generation capabilities to text-generation-webui using Stable Diffusion.

Language:PythonLicense:NOASSERTIONStargazers:45Issues:2Issues:16

llm-political-compass

Web page with political compass quiz results for open LLMs

Language:HTMLStargazers:31Issues:1Issues:0

echoproof

Simple extension for text-generation-webui that injects recent conversation history into the negative prompt with the goal of minimizing the LLM's tendency to fixate on a single word, phrase, or sentence structure.

GPTQ-for-LLaMa-CUDA

A combination of Oobabooga's fork and the main cuda branch of GPTQ-for-LLaMa in a package format.

Language:PythonLicense:Apache-2.0Stargazers:16Issues:0Issues:0

flash-attention

Fast and memory-efficient exact attention - Windows wheels

Language:PythonLicense:BSD-3-ClauseStargazers:15Issues:0Issues:1

ctransformers-cuBLAS-wheels

ctransformers wheels with pre-built CUDA binaries for additional CUDA and AVX versions.

Language:HTMLLicense:MITStargazers:12Issues:1Issues:0

ChatGPT-UI

ChatGPT CSS style

Language:CSSLicense:Apache-2.0Stargazers:8Issues:1Issues:3