yuanenming

system-design-101

Explain complex systems using visuals and simple terms. Help you prepare for system design interviews.

stanford_alpaca

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

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

flash-attention

Fast and memory-efficient exact attention

Startup-CTO-Handbook

The Startup CTO's Handbook, a book covering leadership, management and technical topics for leaders of software engineering teams

qlora

QLoRA: Efficient Finetuning of Quantized LLMs

Megatron-LM

Ongoing research training transformer models at scale

trl

Train transformer language models with reinforcement learning.

inshellisense

IDE style command line auto complete

search_with_lepton

Building a quick conversation-based search demo with Lepton AI.

TinyLlama

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

ChatGPT-AutoExpert

🚀🧠💬 Supercharged Custom Instructions for ChatGPT (non-coding) and ChatGPT Advanced Data Analysis (coding).

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

voila

Voilà turns Jupyter notebooks into standalone web applications

agents

An Open-source Framework for Autonomous Language Agents

alignment-handbook

Robust recipes to align language models with human and AI preferences

opencompass

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

mamba-minimal

Simple, minimal implementation of the Mamba SSM in one file of PyTorch.

direct-preference-optimization

Reference implementation for DPO (Direct Preference Optimization)

prm800k

800,000 step-level correctness labels on LLM solutions to MATH problems

basaran

Basaran is an open-source alternative to the OpenAI text completion API. It provides a compatible streaming API for your Hugging Face Transformers-based text generation models.

self-rewarding-lm-pytorch

Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI

MOSS-RLHF

MOSS-RLHF

fine-tune-mistral

Fine-tune mistral-7B on 3090s, a100s, h100s

deep-learning-pytorch-huggingface

tokenmonster

Ungreedy subword tokenizer and vocabulary trainer for Python, Go & Javascript

textbook_quality

Generate textbook-quality synthetic LLM pretraining data

NeMo-Aligner

Scalable toolkit for efficient model alignment

ArXivQA

WIP - Automated Question Answering for ArXiv Papers with Large Language Models (https://arxiv.taesiri.xyz/)

multipack_sampler

Multipack distributed sampler for fast padding-free training of LLMs