ty33123

TianYun-Liu's starred repositories

MinerU

A one-stop, open-source, high-quality data extraction tool, supports PDF/webpage/e-book extraction.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。

Language:PythonAGPL-3.0961000

places365

The Places365-CNNs for Scene Classification

Language:PythonMIT189700

GeoGuessNet

Visual geolocation using segment cross-attention

Language:Python1700

text_corrector_corpus_auto_generation

该项目致力于从中文文字版PDF文档中，自动化构建出高质量的中文文本纠错语料。

Language:Python300

GeoReasoner

GeoReasoner: Geo-localization with Reasoning in Street Views using a Large Vision-Language Mode

2000

GroundingDINO

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

Language:PythonApache-2.0607100

s2geometry

Computational geometry and spatial indexing on the sphere

Language:C++Apache-2.0227200

CLIP

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

Language:Jupyter NotebookMIT2431800

AddressCLIP

Official implementation and datasets of AddressCLIP

800

reader

Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/

Language:TypeScriptApache-2.0611700

WebCanvas

Connect agents to live web environments evaluation.

Language:PythonMIT15600

langflow

Langflow is a low-code app builder for RAG and multi-agent AI applications. It’s Python-based and agnostic to any model, API, or database.

Language:JavaScriptMIT2547800

free-programming-books

:books: Freely available programming books

CC-BY-4.033202400

modelscope-classroom

Language:Jupyter NotebookApache-2.028100

DoRA

[ICML2024 (Oral)] Official PyTorch implementation of DoRA: Weight-Decomposed Low-Rank Adaptation

Language:PythonNOASSERTION52600

hoppscotch

Open source API development ecosystem - https://hoppscotch.io (open-source alternative to Postman, Insomnia)

Language:TypeScriptMIT6340200

kimi-free-api

🚀 KIMI AI 长文本大模型逆向API白嫖测试【特长：长文本解读整理】，支持高速流式输出、智能体对话、联网搜索、长文档解读、图像OCR、多轮对话，零配置部署，多路token支持，自动清理会话痕迹。

Language:TypeScriptGPL-3.0357300

RAG-Retrieval

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

Language:PythonMIT40500

ChatLaw

ChatLaw：A Powerful LLM Tailored for Chinese Legal. 中文法律大模型

AGPL-3.0677900

trafilatura

Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML

Language:PythonApache-2.0334800

GLM-4

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

Language:PythonApache-2.0429300

GNN4TaskPlan

Official implementation for paper "Can Graph Learning Improve Task Planning?" https://arxiv.org/abs/2405.19119

Language:PythonMIT3400

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

Language:PythonApache-2.01213300