Python 排行榜

My implementation of the model KosmosG from "KOSMOS-G: Generating Images in Context with Multimodal Large Language Models"

This repository provides the official resources for EMNLP 2025 Paper Grounding Multilingual Multimodal LLMs With Cultural Knowledge

FeelingBlue: A Corpus for Understanding the Emotional Connotation of Color in Context, accepted at TACL 2022, presented at ACL 2023

Code release for "GAN-Tree: An Incrementally Learned Hierarchical Generative Framework for Multi-Modal Data Distributions", ICCV 2019

Incorporate Image, Text and Tabular Data with HuggingFace Transformers

[CVPR 2026] Flow Matching for Multimodal Distributions

OMERO.web plugin for the Vitessce multimodal data viewer.

Multimodal document QA: vision + retrieval over PDFs (LLaVA + LlamaIndex)

A high-throughput LLM serving engine with non-uniform KV cache compression, built on vLLM

GPU Service Manager for LLM workloads on Linux/NVIDIA systems.

让 MinerU 在 AMD 显卡上以 vLLM + hybrid-auto-engine 满血运行！ 本项目是对官方文档中 AMD/ROCm 生态支持的有效补充。针对 MinerU 3.x 提供了一套完整的 ROCm 7.x + PyTorch 2.11.0 + vLLM 源码编译与部署方案，解析质量与速度对标 NVIDIA 旗舰显卡。

The Continuous Verification and Optimization layer for self-hosted LLMs

SAM — Smart Agentic Model: CLI coding agent for open-source LLMs. pip install sam-agent

CI scripts designed to build a Pascal-compatible version of vLLM.

A simple custom QLoRA implementation for fine-tuning a language model (LLM) with basic tools such as PyTorch and Bitsandbytes, completely decoupled from Hugging Face.

Unsupervised specificity-guided optimization of Image Captioning models to encourage meaningful diversity in the generated captions. Code for the paper Generating Diverse and Meaningful Captions: Unsupervised Specificity Optimization for Image Captioning (Lindh et al., 2018).

Code for paper "Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation" (ICLR'24)

T5 Fine-tuning on SQuAD Dataset for Question Generation

Source codes and datasets for paper "Zero-1-to-3: Domain-level Zero-shot Cognitive Diagnosis via One Batch of Early-bird Students towards Three Diagnostic Objectives" (AAAI2024)

🍯 自进化 AI 能力研究平台：蜜罐系统 → 沙箱评测引擎 → 训练数据集与 LoRA 微调流水线 / Self-Evolving AI Security Research Platform