MaoXianXin

followers

following

stars

MaoXianXin's starred repositories

bonito

A lightweight library for generating synthetic instruction tuning datasets for your data without GPT.

Language:PythonBSD-3-Clause63600

Scrapegraph-ai

Python scraper based on AI

Language:PythonMIT1387600

Perplexica

Perplexica is an AI-powered search engine. It is an Open source alternative to Perplexity AI

Language:TypeScriptMIT1238200

fabric

fabric is an open-source framework for augmenting humans using AI. It provides a modular framework for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.

Language:Go2045300

TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

Language:C++Apache-2.0793500

text-generation-inference

Large Language Model Text Generation Inference

Language:PythonApache-2.0860200

lmdeploy

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

Language:PythonApache-2.0389800

graphrag

A modular graph-based Retrieval-Augmented Generation (RAG) system

Language:PythonMIT1524200

instructor

structured outputs for llms

Language:PythonMIT715800

awesome-SynthText

A curated list of awesome synthetic data for text location and recognition

SynthText

Code for generating synthetic text images as described in "Synthetic Data for Text Localisation in Natural Images", Ankush Gupta, Andrea Vedaldi, Andrew Zisserman, CVPR 2016.

Language:PythonApache-2.0200100

TextRecognitionDataGenerator

A synthetic data generator for text recognition

Language:PythonMIT318800

donut

Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022

Language:PythonMIT563100

datatrove

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

Language:PythonApache-2.0185600

phi3_vision_language

experiments with microsoft phi3 vision language model. Image captioning, OCR, data extraction

Language:Jupyter Notebook500

florence2-finetuning

Quick exploration into fine tuning florence 2

Language:Jupyter NotebookMIT23300

annotated-transformer

An annotated implementation of the Transformer paper.

Language:Jupyter NotebookMIT549200

matmulfreellm

Implementation for MatMul-free LM.

Language:PythonApache-2.0281400

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Language:PythonApache-2.01876200

mixtral-offloading

Run Mixtral-8x7B models in Colab or consumer desktops

Language:PythonMIT227600

textgrad

TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.

Language:PythonMIT139500

RAG-chatbot-Speckly

This project presents a RAG chat app for the Speckle Developer Documentation.

Language:Jupyter NotebookMIT1900

MiniCPM-V

MiniCPM-V 2.6: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone

Language:PythonApache-2.01068400

llm.c

LLM training in simple, raw C/CUDA

Language:CudaMIT2267400

Qwen-VL

The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.

Language:PythonNOASSERTION456300

OCRDatasets

A collection of OCR-related datasets

8900

ollama

Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.

Language:GoMIT8548100

Playground

Text WebUI extension to add clever Notebooks to Chat mode

Language:Python12600

Qwen2

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

Language:Shell691900

lorax

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

Language:PythonApache-2.0201200