Beast code in Giters

reborm's starred repositories

PaddleOCR

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)

Language:PythonApache-2.039702 431 9024

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

Language:PythonApache-2.017389 159 277

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。

12361 179 20

QAnything

Question and Answer based on Anything.

Language:PythonApache-2.010117 93 308

ragflow

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

Language:PythonApache-2.09105 60 542

unstructured

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

Language:HTMLApache-2.07147 50 976

ChineseNLPCorpus

中文自然语言处理数据集，平时做做实验的材料。欢迎补充提交合并。

Language:Python4123 86 9

lac

百度NLP：分词，词性标注，命名实体识别，词重要性

Language:C++Apache-2.03781 106 247

InternVL

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4V. 接近GPT-4V表现的可商用开源多模态对话模型

Language:PythonMIT3423 37 223

TextRank4ZH

:deciduous_tree:从中文文本中自动提取关键词和摘要

Language:PythonMIT3231 102 34

sqlcoder

SoTA LLM for converting natural language questions to SQL queries

Language:Jupyter NotebookApache-2.02993 32 98

awesome-streamlit

The purpose of this project is to share knowledge on how awesome Streamlit is and can be

Language:HTMLCC-BY-SA-4.01982 45 30

FinGLM

FinGLM: 致力于构建一个开放的、公益的、持久的金融大模型项目，利用开源开放来促进「AI+金融」。

Language:HTML1564 26 27

Awesome-Text2SQL

Curated tutorials and resources for Large Language Models, Text2SQL, Text2DSL、Text2API、Text2Vis and more.

MIT1198 15 4

LLMs_interview_notes

该仓库主要记录大模型（LLMs）算法工程师相关的面试题

Apache-2.01083 9 1

mPLUG-DocOwl

mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding

Language:PythonApache-2.01062 27 79

llm-hallucination-survey

Reading list of hallucination in LLMs. Check out our new survey paper: "Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models"

841 12 3

spRAG

RAG framework for challenging queries over dense unstructured data

Language:PythonMIT455 6 8

Finetune-ChatGLM2-6B

ChatGLM2-6B 全参数微调，支持多轮对话的高效微调。

Language:PythonApache-2.0391 8 22

django-vue-tutorial

用 django-rest-framework 和 vue 搭建前后端分离的个人博客

Language:Vue382 9 4

Prompt-Engineering-Guide-zh-CN

🐙 关于提示词工程（prompt）的指南、论文、讲座、笔记本和资源大全（自动持续更新）

Language:Jupyter NotebookNOASSERTION377 5 3

RAG-Retrieval

Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT,Cross Encoder

Language:PythonMIT311 6 13

MedQA-ChatGLM

🛰️ 基于真实医疗对话数据在ChatGLM上进行LoRA、P-Tuning V2、Freeze、RLHF等微调，我们的眼光不止于医疗问答

Language:Python287 5 12

AlignBench

多维度中文对齐评测基准 | Benchmarking Chinese Alignment of LLMs

Language:Python227 11 25

evol-teacher

Open Source WizardCoder Dataset

Language:PythonApache-2.0138 2 4

Awesome-KBQA

Paper list of KBQA

MIT59 20

text-to-sql-wizardcoder

Leveraging large language models for text-to-SQL synthesis, this project fine-tunes WizardLM/WizardCoder-15B-V1.0 with QLoRA on a custom Spider training dataset. The resultant model, achieves 61% execution accuracy, incorporating database context for validation.

Language:Jupyter Notebook41 6 1

reborm