CLIP-MoE

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Generating Robotic Simulation Tasks via Large Language Models

中文nlp解决方案(大模型、数据、模型、训练、推理)

Image to prompt with BLIP and CLIP

Collection of AWESOME vision-language models for vision tasks

Easily compute clip embeddings and build a clip retrieval system with them

Decentralized deep learning in PyTorch. Built to train models on thousands of volunteers across the world.

Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks

Mixture-of-Experts for Large Vision-Language Models

Must-have resource for anyone who wants to experiment with and build on the OpenAI vision API ?