1737631162 Goto Github PK

baby-llama2-chinese

用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.

bert-vits2

vits2 backbone with multilingual-bert 声音克隆

bitsandbytes-windows-webui

Windows compile of bitsandbytes for use in text-generation-webui.

chatglm3

ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型

chineseembedding

Chinese Embedding collection incling token ,postag ,pinyin,dependency,word embedding.中文自然语言处理向量合集,包括字向量,拼音向量,词向量,词性向量,依存关系向量.共5种类型的向量

controlnext

Controllable video and image Generation, SVD, Animate Anyone, ControlNet, ControlNeXt, LoRA

deepke

An Open Toolkit for Knowledge Graph Extraction and Construction published at EMNLP2022 System Demonstrations.

easyspider

A visual no-code/code-free web crawler/spider易采集：一个可视化浏览器自动化测试/数据采集/爬虫软件，可以无代码图形化的设计和执行爬虫任务。别名：ServiceWrapper面向Web应用的智能化服务封装系统。

fastllm

纯c++的全平台llm加速库，支持python调用，chatglm-6B级模型单卡可达10000+token / s，支持glm, llama, moss基座，手机端流畅运行

glm-4

GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

image-captioning-pytorch

图像中文描述+视觉注意力

jittorllms

计图大模型推理库，具有高性能、配置要求低、中文支持好、可移植等特点

llama3v

A SOTA vision model built on top of llama3 8B.

llm-export-onnx

llm-export can export llm model to onnx.

llm-quickstart

极客时间-大语言模型快速入门（理论学习与微调实战）

llm_0-1

pre train a new llm

lmdeploy

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

mediacrawler

mini-llama2-chinese

想要从零开始训练一个中文的mini大语言模型，可以进行基本的对话，模型大小根据手头的机器决定

mini_llm

从零开始训练模型

minicpm-v

轻量化大模型（支持图像理解）MiniCPM-Llama3-V 2.5: A GPT-4V Level Multimodal LLM on Your Phone

onnxllm

Large Language Model Onnx Inference Framework

paddlenlp

👑 Easy-to-use and powerful NLP and LLM 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 etc.

pdf2md

一站式开源高质量数据提取工具，支持PDF/网页/多格式电子书提取。

powerpoint-extractor

A simple script to extract images, text, and presenter notes from a folder full of PowerPoint files.

pptx2md

a pptx to markdown converter

python3_wiki_word2vec

基于python3训练中文wiki词向量、字向量、拼音向量

pytorch-book

PyTorch tutorials and fun projects including neural talk, neural style, poem writing, anime generation

qwen-tensorrt-llm

rasa

💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants