luoruijie Goto Github PK

alpaca-lora

Instruct-tune LLaMA on consumer hardware

awesome-nlp-resources

a collection of NLP projects&tools. 自然语言处理方向项目和工具集合。

bert-squad

SQuAD Question Answering Using BERT, PyTorch

bootstrapping

Code examples from the book

cacluate_datassert

chatglm-finetuning

基于ChatGLM-6B、ChatGLM2-6B、ChatGLM3-6B模型，进行下游具体任务微调，涉及Freeze、Lora、P-tuning、全参微调等

chatgpt-chatbot

This repository will guide you to create ChatGPT like chatbot using OpenAI's GPT 3.5 model

chinese-newwordrecognition

专业领域词库构建/中文新词发现/专业词库发现

class_acitvity_identify

课堂活动识别

diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

doccano

Open source annotation tool for machine learning practitioners.

docquery

An easy way to extract information from documents

generative-ai-on-aws

Generative AI on AWS（一个LLMs微调的课程）

grok-1

Grok open release

harvesttext

文本挖掘和预处理工具（文本清洗、新词发现、情感分析、实体识别链接、关键词抽取、知识抽取、句法分析等），无监督或弱监督方法

hierarchical-multi-label-text-classification

The code of CIKM'19 paper《Hierarchical Multi-label Text Classification: An Attention-based Recurrent Network Approach》

llama-factory

Unify Efficient Fine-Tuning of 100+ LLMs

llama-recipes

Examples and recipes for Llama 2 model

mutil_label_calssification_ccks_2021

多标签文本分类

my-team-learning

我的Datawhale组队学习，在线阅读地址：https://relph1119.github.io/my-team-learning

paddle_srgan

基于飞桨复现SRGAN模型，一种用于图像超分辨率（SR）的生成对抗网络（GAN），能够推断4倍放大因子的照片般逼真的自然图像。

paddlenlp

Easy-to-use and powerful NLP library with Awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications, including Neural Search, Question Answering, Information Extraction and Sentiment Analysis end-to-end system.

pclue

pCLUE: 1000000+多任务提示学习数据集

poocr

pip install poocr

prompt

收集的提示词

pycorrector

pycorrector is a toolkit for text error correction. 文本纠错，Kenlm，ConvSeq2Seq，BERT，MacBERT，ELECTRA，ERNIE，Transformer，T5等模型实现，开箱即用。

ruantong

我在软通时的一些纪录

semantic-text-similarity

an easy-to-use interface to fine-tuned BERT models for computing semantic similarity in clinical and web text. that's it.

source-code-notebook

关于一些经典论文源码的逐行中文笔记

t5-pegasus-chinese

基于GOOGLE T5中文生成式模型的摘要生成/指代消解，支持batch批量生成，多进程