Instruction Following Agents with Multimodal Transforemrs
MIT License
Statistics for this project are still being loaded, please check back later.
Official code of CVPR 2021's PLOP: Learning without Forgetting for Continual Semantic Segmentation
A PyTorch Lightning solution to training OpenAI's CLIP from scratch.
Embed arbitrary modalities (images, audio, documents, etc) into large language models.
We present NoticIA, a dataset consisting of 850 Spanish news articles featuring prominent clickba...
Lightning implementation of seq2seq dialog model
本项目基于PaddleDetection目标检测开发套件,选取1.3M超轻量PPYOLO tiny进行项目开发,并部署于windows端。
Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transfo...
Language Quantized AutoEncoders
Transformer with Untied Positional Encoding (TUPE). Code of paper "Rethinking Positional Encoding...
Shape and pose estimation using discretized signed distance fields
Fine tuning experiments for the GPT-2 model by OpenAI.
Easiest way of fine-tuning HuggingFace video classification models
Chain-of-Hindsight, A Scalable RLHF Method