ShuoTang123

yq

Command-line YAML, XML, TOML processor - jq wrapper for YAML/XML/TOML documents

MOSS-RLHF

MOSS-RLHF

pal

PaL: Program-Aided Language Models (ICML 2023)

ZIP

sglang

SGLang is a fast serving framework for large language models and vision language models.

dclm

DataComp for Language Models

persona-hub

Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"

ntscraper

Scrape from Twitter using Nitter instances

HALOs

A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).

ilya-sutskever-recommended-reading

It is said that, Ilya Sutskever gave John Carmack this reading list of ~ 30 research papers on deep learning.

MoA

Together Mixture-Of-Agents (MoA) – 65.1% on AlpacaEval with OSS models

magpie

Official repository for "Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing". Your efficient and high-quality synthetic data generation pipeline!

DeepSeek-V2

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

chat_templates

Chat Templates for 🤗 HuggingFace Large Language Models

spring2024-lectures

llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

FedLLM-Bench

AgentGym

Code and implementations for the paper "AgentGym: Evolving Large Language Model-based Agents across Diverse Environments" by Zhiheng Xi et al.

social_simulation

website repo for agent-based social movement simulation

stanford_alpaca

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

WizardLM

LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath

deita

Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]

SimPO

SimPO: Simple Preference Optimization with a Reference-Free Reward

OpenRLHF

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & Mixtral)

llama3-from-scratch

llama3 implementation one matrix multiplication at a time

TwitterCrawler

抓取twitter数据，可根据时间、话题、用户名等条件抓取数据，twitter爬虫

CRSEC

accelerate

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

self-speculative-decoding

Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**

SpeculativeDecodingPapers

📰 Must-read papers and blogs on Speculative Decoding ⚡️