jquesnelle

yarn

YaRN: Efficient Context Window Extension of Large Language Models

txt2imghd

A port of GOBIG for Stable Diffusion

transformers-openai-api

An OpenAI Completions API compatible server for NLP transformers models

crt-terminal

Retro styled terminal shell

literAI

Generate visual podcasts about novels using open source models

sat-reading

ctranslate2-rs

Rust bindings for CTranslate2

notebooks

CTranslate2

Fast inference engine for Transformer models

guidance

A guidance language for controlling large language models.

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

axolotl

Go ahead and axolotl questions

EasyContext

Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.

flash-attention

Fast and memory-efficient exact attention

ggml

Tensor library for machine learning

ghostwriter

hooligan-hymnal-app

llama.cpp

Port of Facebook's LLaMA model in C/C++

llm-chain

`llm-chain` is a powerful rust crate for building chains in large language models allowing you to summarise text and complete complex tasks

lm-evaluation-harness

A framework for few-shot evaluation of autoregressive language models.

nanotron

Minimalistic large language model 3D-parallelism training

ollama

Get up and running with Llama 2, Mistral, and other large language models locally.

Open-Assistant

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

plugins-workspace

All of the official Tauri plugins in one place!

promptsource

Toolkit for creating, sharing and using natural language prompts.

qlora

QLoRA: Efficient Finetuning of Quantized LLMs

t-zero

Reproduce results and replicate training fo T0 (Multitask Prompted Training Enables Zero-Shot Task Generalization)

textsum

CLI & Python API to easily summarize text-based files with transformers

tokenizers

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production