Pinned Repositories
bert
添加了部分中文注释，以便理解的bert。TensorFlow code and pre-trained models for BERT
Chinese-NER-Efficient-GlobalPointer
中文NER的基线模型，可作为实际场景中的V1版
chinese_ner_bert_lstm_crf
pytorch版本的lstm+crf和bert+crf的中文ner，包含数据和完整代码
COIG-PC-Downloader
多进程下载COIG-PC数据集
CustomViewForClock
a demo for custom view
CustomViewGroupForBlog
demo of custom viergroup
cutword
一个简单快速的分词、命名实体识别工具
easycorrector
简单方便的中文纠错算法集合
error_text_gen
用于生成文本纠错模型(如Gector)需要的大量数据。
ReactNativeWithNativeApp
Demo For integrate React Naitve into existing Android app
liwenju0's Repositories
liwenju0/COIG-PC-Downloader
多进程下载COIG-PC数据集
liwenju0/Awesome-Chinese-LLM
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
liwenju0/baidu-qa-100w
:table: 百度QA100万数据集
liwenju0/BentoML
Build Production-Grade AI Applications
liwenju0/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。
liwenju0/ChatWK
Usings LLM chat with knowledges
liwenju0/cutting_edge_nlp_algo_with_keras3
从最早接触keras开始，就很喜欢它清晰简洁的api设计，我之前还专门读过一些Kerar底层的源码。
liwenju0/devv
An AI-powered search engine for developers.
liwenju0/FastGPT
FastGPT is a knowledge-based question answering system based on the LLM language model, providing out-of-the-box capabilities for data processing, model invocation, and more. It also allows for complex question answering scenarios through visual workflow orchestration using Flow!
liwenju0/flashtext
Extract Keywords from sentence or Replace keywords in sentences.
liwenju0/insanely-fast-whisper
liwenju0/InstructUIE
Universal information extraction with instruction learning
liwenju0/Langchain-Chatchat
Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM 等语言模型的本地知识库问答 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM) QA app with langchain
liwenju0/LangGPT
LangGPT: Empowering everyone to become a prompt expert!🚀 Structured Prompt，Language of GPT, 结构化提示词，结构化Prompt
liwenju0/lightllm
LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.
liwenju0/LLaMA-Efficient-Tuning
Easy-to-use LLM fine-tuning framework (LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, ChatGLM2)
liwenju0/LLMDataHub
A quick guide (especially) for trending instruction finetuning datasets
liwenju0/ltp
Language Technology Platform
liwenju0/mamba-minimal
Simple, minimal implementation of Mamba in one file of PyTorch.
liwenju0/MedicalGPT
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现包括二次预训练、有监督微调、奖励建模、强化学习训练。
liwenju0/Megatron-LLaMA
Best practice for training LLaMA models in Megatron-LM
liwenju0/mojo
The Mojo Programming Language
liwenju0/OCR_DataSet
收集并整理有关OCR的数据集并统一标注格式，以便实验需要
liwenju0/OpenChatKit
liwenju0/pytextclassifier
pytextclassifier is a toolkit for text classification. 文本分类，LR，Xgboost，TextCNN，FastText，BiLSTM_Attention，BERT等模型实现，开箱即用。
liwenju0/PytorchOCR
基于Pytorch的OCR工具库，支持常用的文字检测和识别算法
liwenju0/RedPajama-Data
The RedPajama-Data repository contains code for preparing large datasets for training large language models.
liwenju0/RuoYi-Vue3
:tada: (RuoYi)官方仓库 基于SpringBoot，Spring Security，JWT，Vue3 & Vite、Element Plus 的前后端分离权限管理系统
liwenju0/unsloth
5X faster 50% less memory LLM finetuning
liwenju0/whisper.cpp
Port of OpenAI's Whisper model in C/C++