Contexts Optical Compression

将SmolVLM2的视觉头与Qwen3-0.6B模型进行了拼接微调

Everything about the SmolLM and SmolVLM family of models

AI-Powered Photos App for the Decentralized Web 🌈💎✨

A CPU Realtime VLM in 500M. Surpassed Moondream2 and SmolVLM. Training from scratch with ease.

Align Anything: Training All-modality Model with Feedback

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

yolov5 deepsort 行人 车辆 跟踪 检测 计数

Optimizing inference proxy for LLMs

Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

🔥 The Web Data API for AI - Turn entire websites into LLM-ready markdown or structured data

Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks

MiniCPM-V 4.5: A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone

主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

Augmentation pipeline for rendering synthetic paper printing, faxing, scanning and copy machine processes

TexTeller can convert image to latex formulas (image2latex, latex OCR) with higher accuracy and exhibits superior generalization ability, enabling it to cover most usage scenarios.

UniMERNet: A Universal Network for Real-World Mathematical Expression Recognition

本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）

A Next-Generation Training Engine Built for Ultra-Large MoE Models

Ongoing research training transformer models at scale

Retrieval and Retrieval-augmented LLMs

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"

Java Geometry Expert

Scalable data pre processing and curation toolkit for LLMs

The state-of-the-art image restoration model without nonlinear activation functions.

用于大模型 RLHF 进行人工数据标注排序的工具。A tool for manual response data annotation sorting in RLHF stage.