thuwth's Projects
🇫🇷 Oh my tmux! My self-contained, pretty & versatile tmux configuration made with ❤️
Instruct-tune LLaMA on consumer hardware
An experimental open-source attempt to make GPT-4 fully autonomous.
微信小程序开发资源汇总 :100:
BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)
Chinese-LLaMA 、Chinese-Falcon 基础模型;ChatFlow中文对话模型;中文OpenLLaMA模型;NLP预训练/指令微调数据集
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案,结构参考alpaca
Paper List for Contrastive Learning for Natural Language Processing
State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Open source annotation tool for machine learning practitioners.
The official tool for transforming doccano format into common dataset formats.
Data augmentation for NLP, presented at EMNLP 2019
Shepherd: A lightweight, foundational framework enabling federated instruction tuning for large language models
fitlog是一款在深度学习训练中用于辅助用户记录日志和管理代码的工具
An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.
LightSeq: A High Performance Library for Sequence Processing and Generation
A quick guide (especially) for trending instruction finetuning datasets
该仓库主要记录 NLP 算法工程师相关的顶会论文研读笔记
Data augmentation for NLP
Picture bed of Typora
Store the picture of Typora
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
Code and documentation to train Stanford's Alpaca models, and generate the data.
Config files for my GitHub profile.
🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.
A playbook for systematically maximizing the performance of deep learning models.