OpenChat: Advancing Open-source Language Models with Imperfect Data

リアルタイムボイスチェンジャー Realtime Voice Changer

Voice data <= 10 mins can also be used to train a good VC model!

🔊 Text-prompted Generative Audio Model - With the ability to clone voices

Python bindings for llama.cpp

한국어 sentence bert

Deploy llama.cpp compatible Generative AI LLMs on AWS Lambda!

Inference code for LLaMA models

Github for "Extraction of Comprehensive Drug Safety Information from Adverse Drug Event Narratives in Spontaneous Reporting System"

Fine-tuning 6-Billion GPT-J (& other models) with LoRA and 8-bit compression

Clone a voice in 5 seconds to generate arbitrary speech in real-time

multi_label_bert

CORS Anywhere is a NodeJS reverse proxy which adds CORS headers to the proxied request.