OpenChat: Advancing Open-source Language Models with Imperfect Data

Fast Sprite Decomposition from Animated Graphics [ECCV2024]

Framework for specializing LLMs for retrieval-augmented-generation tasks using fine-tuning.

Medical SAM 2: Segment Medical Images As Video Via Segment Anything Model 2

AirLLM 70B inference with single 4GB GPU

PyTorch3D is FAIR's library of reusable components for deep learning with 3D data

Summary of publicly available ressources such as code, datasets, and scientific papers for the FLAME 3D head model

An Extensible Deep Learning Library

Official Implementation of "Open-Vocabulary Audio-Visual Semantic Segmentation" [ACM MM 2024 Oral].

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.

a LLM-based Multi-agent Framework of Web Search Engine similar to Perplexity.ai Pro and SearchGPT

[ACL 2024 Demo] SeaLLMs - Large Language Models for Southeast Asia

ChatGPT 中文调教指南。各种场景使用指南。学习怎么让它听你的话。

Official implementation of Cycle3D: High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction Cycle

Diffusion Feedback Helps CLIP See Better

Landing Page for All Things Source Separation

🌍 Repository for "AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agent", ACL2024

Robot Spin Pens

The memory layer for Personalized AI

Efficient Cell Nuclei Instance Segmentation with Large Convolution Kernels

[ACL 2024] Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning

User-friendly WebUI for LLMs (Formerly Ollama WebUI)

Aura is like Siri, but in your browser. An AI voice assistant optimized for low latency responses.

Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.

Diffree: Text-Guided Shape Free Object Inpainting with Diffusion Model

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

[ECCV 2024] Efficient Inference of Vision Instruction-Following Models with Elastic Cache