练习英语，一次敲击，一点进步；Practice English, one strike, one step forward

open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.

Language server protocol implementation for VSCode. This allows implementing language services in JS/TS running on node.js

Trained models & code to predict toxic comments on all 3 Jigsaw Toxic Comment Challenges. Built using ⚡ Pytorch Lightning and 🤗 Transformers. For access to our API, please email us at contact@unita…

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

A collection of awesome text-to-image generation studies.