lazyc81

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。

pandoc-latex-template

A pandoc LaTeX template to convert markdown files to PDF or LaTeX.

img2latex-mathpix

Mathpix has changed their billing policy and no longer has free monthly API requests. This repo is now archived and will not receive any updates for the foreseeable future.

Pix2Text

An Open-Source Python3 tool for recognizing layouts, tables, math formulas (LaTeX), and text in images, converting them into Markdown format. A free alternative to Mathpix, empowering seamless conversion of visual content into text-based representations. 80+ languages are supported.

open-parse

Improved file parsing for LLM’s

rebased

Official implementation of the paper "Linear Transformers with Learnable Kernel Functions are Better In-Context Models"

zzzArchived_arxiv-readability

Pilot project to render HTML5 from arXiv LaTeX sources

synctex

Synchronization for TeX

ar5ivist

A turnkey command for converting a LaTeX source to ar5iv-style HTML

Qwen-Agent

Agent framework and applications built upon Qwen2, featuring Function Calling, Code Interpreter, RAG, and Chrome extension.

MobileAgent

Mobile-Agent: The Powerful Mobile Device Operation Assistant Family

mPLUG-DocOwl

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

based

Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"

pdftotree

:evergreen_tree: A tool for converting PDF into hOCR with text, tables, and figures being recognized and preserved.

Yi

A series of large language models trained from scratch by developers @01-ai

Qwen2

Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.

txtai

💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows

deepdoctection

A Repo For Document AI

nlm-ingestor

This repo provides the server side code for llmsherpa API to connect. It includes parsers for various file formats.

llmsherpa

Developer APIs to Accelerate LLM Projects

Parsr

Transforms PDF, Documents and Images into Enriched Structured Data

marker

Convert PDF to markdown quickly with high accuracy

unstructured

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

mega

Sequence modeling with Mega.

infinite-former

CAB

gpt-neox

An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

xformers

Hackable and optimized Transformers building blocks, supporting a composable construction.

papermage

library supporting NLP and CV research on scientific papers

awesome_LLMs_interview_notes

LLMs interview notes and answers:该仓库主要记录大模型（LLMs）算法工程师相关的面试题和参考答案