<⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

Create web-based user interfaces with Python. The nice way.

100 numpy exercises (with solutions)

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

Minimal reproduction of DeepSeek R1-Zero

High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

The LLM Evaluation Framework

A curated list of awesome mathematics resources

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

A collaboration friendly studio for NeRFs

Go ahead and axolotl questions

Large Language Model Text Generation Inference

ImageBind One Embedding Space to Bind Them All

Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

fast-stable-diffusion + DreamBooth

BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)

An open source python library for automated feature engineering

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

Repo for external large-scale work

Image processing in Python

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

[EMNLP'23, ACL'24] 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.

Outpainting with Stable Diffusion on an infinite canvas

Simple RL training for reasoning

LLM as a Chatbot Service

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration