chiennv2000

text-generation-inference

Large Language Model Text Generation Inference

torchscale

Foundation Architecture for (M)LLMs

neurips_llm_efficiency_challenge

NeurIPS Large Language Model Efficiency Challenge: 1 LLM + 1GPU + 1Day

openchat

OpenChat: Advancing Open-source Language Models with Imperfect Data

ProphetNet

A research project for natural language generation, containing the official implementations by MSRA NLC team.

direct-preference-optimization

Reference implementation for DPO (Direct Preference Optimization)

OmniEvent

A comprehensive, unified and modular event extraction toolkit.

baize-chatbot

Let ChatGPT teach your own chatbot in hours with a single GPU!

lm-evaluation-harness

flatness

LaViLa

Code release for "Learning Video Representations from Large Language Models"

trlx

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

denoising-diffusion-gan

Tackling the Generative Learning Trilemma with Denoising Diffusion GANs https://arxiv.org/abs/2112.07804

latex-examples

Simple LaTeX examples

MiniGPT-4

Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

web-llm

High-performance In-browser LLM Inference Engine

LLaMA-Cult-and-More

Large Language Models for All, 🦙 Cult and More, Stay in touch !

LLM-finetuning-scripts

torchrl_examples

Training examples using TorchRL repo

rl

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

Fair-Diffusion

trl

Train transformer language models with reinforcement learning.

self-instruct

Aligning pretrained language models with instruction data generated by themselves.

self-refine

LLMs can generate feedback on their work, use it to improve the output, and repeat this process iteratively.

consistency_models

Official repo for consistency models.

stanford_alpaca

Code and documentation to train Stanford's Alpaca models, and generate the data.

DA-Transformer

Official Implementation for the ICML2022 paper "Directed Acyclic Transformer for Non-Autoregressive Machine Translation"

prompt-in-context-learning

Awesome resources for in-context learning and prompt engineering: Mastery of the LLMs such as ChatGPT, GPT-3, and FlanT5, with up-to-date and cutting-edge updates.

chatgpt-retrieval-plugin

The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.

RWKV-LM

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.