qixuxiang

LLM101n

LLM101n: Let's build a Storyteller

freqtrade

Free, open source crypto trading bot

flash-attention

Fast and memory-efficient exact attention

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。

Megatron-LM

Ongoing research training transformer models at scale

PowerInfer

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

CogVideo

Text-to-video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

InternVL

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

gpu.cpp

A lightweight library for portable low-level GPU computation using WebGPU.

llm-scraper

Turn any webpage into structured data using LLMs

Image-Downloader

Download images from Google, Bing, Baidu. 谷歌、百度、必应图片下载.

GLIP

Grounded Language-Image Pre-training

Monkey

【CVPR 2024 Highlight】Monkey (LMM): Image Resolution and Text Label Are Important Things for Large Multi-modal Models

stockbot-on-groq

StockBot powered by Groq: Lightning Fast AI Chatbot that Responds With Live Interactive Stock Charts, Financials, News, Screeners, and More. Powered by Llama3-70b on Groq, Vercel AI SDK, and TradingView Widgets.

extraction-framework

The software used to extract structured data from Wikipedia

VisionLLM

VisionLLM Series

MINT-1T

MINT-1T: A one trillion token multimodal interleaved dataset.

ktransformers

A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

TensorRT-Model-Optimizer

TensorRT Model Optimizer is a unified library of state-of-the-art model optimization techniques such as quantization, sparsity, distillation, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM or TensorRT to optimize inference speed on NVIDIA GPUs.

Vitron

A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing

Awesome-LLM-Tabular

Awesome-LLM-Tabular: a curated list of Large Language Model applied to Tabular Data

OmniCorpus

OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text

OV-DINO

Official implementation of OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion

magic-html

clip-pytorch

这是一个clip-pytorch的模型，可以训练自己的数据集。

VoCo-LLaMA

VoCo-LLaMA: This repo is the official implementation of "VoCo-LLaMA: Towards Vision Compression with Large Language Models".

llama.cpp

Port of Facebook's LLaMA model in C/C++

MMLongBench-Doc

Official Repository of MMLONGBENCH-DOC: Benchmarking Long-context Document Understanding with Visualizations

cutlass_flash_atten_fp8

使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention

HistoricalDataForTradeBacktest

Historical Trade Data For Backtests