Official Repository of paper VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding

Official code for MiniGPT4-video

🔥🔥🔥 Web-based linux server management control panel. / 现代化、开源的 Linux 服务器运维管理面板。

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

Get up and running with Llama 3, Mistral, Gemma 2, and other large language models.

My implementation of "Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution"

Reference implementation for DPO (Direct Preference Optimization)

Document Artifical Intelligence

Elysium: Exploring Object-level Perception in Videos via MLLM

Extract hardcoded subtitles from videos using machine learning

RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.

Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

Cobra: Extending Mamba to Multi-modal Large Language Model for Efficient Inference

Official code implementation of Vary: Scaling Up the Vision Vocabulary of Large Vision Language Models.

视频硬字幕提取，生成srt文件。无需申请第三方API，本地实现文本识别。基于深度学习的视频字幕提取框架，包含字幕区域检测、字幕内容提取。A GUI tool for extracting hard-coded subtitle (hardsub) from videos and generating srt files.

A Native-PyTorch Library for LLM Fine-tuning

[GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly …

official repository of aiXcoder-7B Code Large Language Model

Towards Video Text Visual Question Answering: Benchmark and Baseline

A large Cross-Modal Video Retrieval Dataset with Reading Comprehension

Video datasets

InternLM-XComposer2 is a groundbreaking vision-language large model (VLLM) excelling in free-form text-image composition and comprehension.

An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)

Inference Llama 2 in one file of pure C

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

MiniCPM-2B: An end-side LLM outperforming Llama2-13B.

[CVPR 2024] Prompt Highlighter: Interactive Control for Multi-Modal LLMs

Official Implementation for LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models

leaked prompts of GPTs