Lightning implementation of seq2seq dialog model
Find better generation parameters for your LLM
Transformer models implementation for training 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...
A curated list of useful Python packages for data geeks
An implementation of training for GPT2, supports TPUs
Instruction Following Agents with Multimodal Transforemrs
TristouNet: Triplet Loss for Speaker Turn Embedding
Chain-of-Hindsight, A Scalable RLHF Method
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。
Transformer with Untied Positional Encoding (TUPE). Code of paper "Rethinking Positional Encoding...
NLP预/后处理工具。