koalazf99

OpenDevin

🐚 OpenDevin: Code Less, Make More

LLaMA-Factory

A WebUI for Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

devika

Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective. Devika aims to be a competitive open-source alternative to Devin by Cognition AI.

litgpt

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

DiT

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

promptbase

All things prompt engineering

LLMLingua

To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

MiniGemini

Official implementation for Mini-Gemini

open-parse

Improved file parsing for LLM’s

DeepSeek-VL

DeepSeek-VL: Towards Real-World Vision-Language Understanding

starcoder2

Home of StarCoder2!

lmms-eval

Accelerating the development of large multimodal models (LMMs) with lmms-eval

llm-colosseum

Benchmark LLMs by fighting in Street Fighter 3! The new way to evaluate the quality of an LLM

Triton-Puzzles

Puzzles for learning Triton

flashinfer

FlashInfer: Kernel Library for LLM Serving

text-dedup

All-in-one text de-duplication

Megatron-LLM

distributed trainer for LLMs

awesome-tool-llm

research-career-tools

QuRating

[ICML 2024] Selecting High-Quality Data for Training Language Models

simulated-trial-and-error

scaling

Language models scale reliably with over-training and on downstream tasks

sailor-llm

Sailor: Open Language Models for South-East Asia

the-stack-v2

Code for the curation of The Stack v2 and StarCoder2 training data

math-evaluation-harness

A simple toolkit for benchmarking LLMs on mathematical reasoning tasks. 🧮✨

bitnet

Modeling code for a BitNet b1.58 Llama-style model.

turking-bench

Web-grounded natural language instructions

self-prompting

option_trading_resources

Comprehensive options trading resource including books, papers, tools, etc. (Work In Progress)