An extremely fast Python package and project manager, written in Rust.

Generative AI extensions for onnxruntime

FlagEval is an evaluation toolkit for AI large foundation models.

A tool to modify ONNX models in a visualization fashion, based on Netron and Flask.

On-device AI across mobile, embedded and edge for PyTorch

Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.

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

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Test your prompts, agents, and RAGs. Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with comma…

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

State-of-the-Art Text Embeddings

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

Documentation that simply works

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Fast and memory-efficient exact attention

An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.

A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)

Development repository for the Triton language and compiler

Transformer related optimization, including BERT, GPT

Toolkit for creating, sharing and using natural language prompts.

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

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.

Official release of InternLM series (InternLM, InternLM2, InternLM2.5, InternLM3).

Implementation of Meta-Voicebox : The first generative AI model for speech to generalize across tasks with state-of-the-art performance.

A parser, editor and profiler tool for ONNX models.

OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset

Instruct-tune LLaMA on consumer hardware