thuwth Goto Github PK

.tmux

🇫🇷 Oh my tmux! My self-contained, pretty & versatile tmux configuration made with ❤️

alpaca-lora

Instruct-tune LLaMA on consumer hardware

auto-gpt

An experimental open-source attempt to make GPT-4 fully autonomous.

awesome-wechat-weapp

微信小程序开发资源汇总 :100:

bertviz

BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)

chinese-falcon

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

chinese-llama-alpaca

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

chinese-vicuna

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

contrastive-learning-nlp-papers

Paper List for Contrastive Learning for Natural Language Processing

deeplearningexamples

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

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

doccano

Open source annotation tool for machine learning practitioners.

doccano-transformer

The official tool for transforming doccano format into common dataset formats.

eda_nlp

Data augmentation for NLP, presented at EMNLP 2019

federatedgpt-shepherd

Shepherd: A lightweight, foundational framework enabling federated instruction tuning for large language models

fitlog

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

gpt-neo

An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.

lightseq

LightSeq: A High Performance Library for Sequence Processing and Generation

llmdatahub

A quick guide (especially) for trending instruction finetuning datasets

minebert

minebert-

nlp_paper_study

该仓库主要记录 NLP 算法工程师相关的顶会论文研读笔记

nlpaug

Data augmentation for NLP

pic-bed

Picture bed of Typora

picturebed

Store the picture of Typora

rwkv-lm

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.

stanford_alpaca

Code and documentation to train Stanford's Alpaca models, and generate the data.

thuwth

Config files for my GitHub profile.

transformers

🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.

tuning_playbook

A playbook for systematically maximizing the performance of deep learning models.