Yonas's repositories
train_llama
由于项目需要,整理出llama微调代码,供参考
AI-Paper-Collector
Fully-automated scripts for collecting AI-related papers
BERT_MRC_CLS
Build model frameworks base on NEZHA to include top conference papers in the field of nlp, because it will help me find ID features
Chinese-BERT-wwm
Pre-Training with Whole Word Masking for Chinese BERT(中文BERT-wwm系列模型)
continual-learning-papers
Continual Learning papers list, curated by ContinualAI
easyquotation
实时获取新浪 / 腾讯 的免费股票行情 / 集思路的分级基金行情
label-studio
Label Studio is a multi-type data labeling and annotation tool with standardized output format
PaddleNLP
👑 Easy-to-use and powerful NLP library with 🤗 Awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications, including 🗂Text Classification, 🔍 Neural Search, ❓ Question Answering, ℹ️ Information Extraction, 📄 Document Intelligence, 💌 Sentiment Analysis and 🖼 Diffusion AIGC system etc.
Paper-Writing-Tips
Paper Writing Tips
pytorch-crf
(Linear-chain) Conditional random field in PyTorch.
qlib
Qlib is an AI-oriented quantitative investment platform, which aims to realize the potential, empower the research, and create the value of AI technologies in quantitative investment. With Qlib, you can easily try your ideas to create better Quant investment strategies. An increasing number of SOTA Quant research works/papers are released in Qlib.
SciencePlots
Matplotlib styles for scientific plotting
smiley-sans
得意黑 Smiley Sans:一款在人文观感和几何特征中寻找平衡的中文黑体
alipay-sdk-python-all
支付宝开放平台 Alipay SDK for Python
chatgpt-demo-original
Minimal UI for ChatGPT.
ChatGPT-Next-Web
A well-designed cross-platform ChatGPT UI (Web / PWA / Linux / Win / MacOS). 一键拥有你自己的跨平台 ChatGPT 应用。
Chinese-LLaMA-Alpaca-2
中文 LLaMA-2 & Alpaca-2 大模型二期项目 + 本地CPU/GPU训练部署 (Chinese LLaMA-2 & Alpaca-2 LLMs)
gpt_academic
为GPT/GLM等LLM大语言模型提供实用化交互接口,特别优化论文阅读/润色/写作体验,模块化设计,支持自定义快捷按钮&函数插件,支持Python和C++等项目剖析&自译解功能,PDF/LaTex论文翻译&总结功能,支持并行问询多种LLM模型,支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。
SSPanel-Uim
SSPanel V3 魔改再次修改版
TRACE
TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models
tutorials
PyTorch tutorials.
yanbao_indicator_extract
21年做的研报指标抽取项目。分3个模型pipeline去做:分类(是否有指标)-抽取(NER抽取指标)-抽取指标的属性(依赖给定指标,抽context中对应的属性,MRC的start/end指针做)