Hunyuan 3D Part Segmentation and Generation Pipeline

An AI Hedge Fund Team

New libcamera based python library

real time face swap and one-click video deepfake with only a single image

SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

On-device Speech Recognition for Apple Silicon

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

Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.

Llama 2 Everywhere (L2E)

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

Pythonic Smart Contract Language for the EVM

Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023)

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

The definitive Web UI for local AI, with powerful features and easy setup.

QLoRA: Efficient Finetuning of Quantized LLMs

Let ChatGPT teach your own chatbot in hours with a single GPU!

Medical Question Answering Dataset of 47,457 QA pairs created from 12 NIH websites

An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"

Ecoute is a live transcription tool that provides real-time transcripts for both the user's microphone input (You) and the user's speakers output (Speaker) in a textbox.

End-to-End Zero-Shot Voice Conversion with Location-Variable Convolutions

TriAAN-VC: Triple Adaptive Attention Normalization for Any-to-Any Voice Conversion

QuickVC: Any-to-many Voice Conversion Using Inverse Short-time Fourier Transform for Faster Conversion

The Modular Platform (includes MAX & Mojo)

A hirevue question cracker.

🦜🔗 The platform for reliable agents.

LLM inference in C/C++

ESP32 application to change a voice to be eg stormtrooper or dalek sounding, either in real time for cosplay or as a recording. Recordings can be downloaded to the browser as a WAV file for playbac…

Query your Apple Health data with natural language 💬 🩺

Port of OpenAI's Whisper model in C/C++