ranck626

MMTrustEval

A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust)

LLaVA-MOSS2

Modified LLaVA framework for MOSS2, and makes MOSS2 a multimodal model.

AI-Scientist

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

AI_Gen_Novel

基于大语言模型(LLM)和多智能体(Multi-Agent)，探究AI写小说能力的边界

RemoteCLIP

🛰️ Official repository of paper "RemoteCLIP: A Vision Language Foundation Model for Remote Sensing" (IEEE TGRS)

CLIP-rsicd

clip-lora

WHU-OPT-SAR-dataset

Open source dataset; multimodal fusion；remote sensing；optical images; SAR images；deep learning

ONE-PEACE

A general representation model across vision, audio, language modalities. Paper: ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities

dive-into-llms

《动手学大模型Dive into LLMs》系列编程实践教程

MultiMon

Tip-Adapter

CLIP-LoRA

An easy way to apply LoRA to CLIP. Implementation of the paper "Low-Rank Few-Shot Adaptation of Vision-Language Models" (CLIP-LoRA) [CVPRW 2024].

CLIP-Adapter

SAR-CLIP

LanguageBind

【ICLR 2024🔥】 Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment

ImageBind-LoRA

Fine-tuning "ImageBind One Embedding Space to Bind Them All" with LoRA

Chinese-LLaVA

支持中英文双语视觉-文本对话的开源可商用多模态模型。

Fine-Tuning-the-Image-Encoder-of-clip-using-pre-Trained-CLIP-ViT-Large-Patch14

Optimize CLIP-ViT-Large-Patch14.ipynb with our tailored image encoder fine-tuning script. Quickly adapt the model to your needs for enhanced performance on image-based tasks.

executor-image-clip-encoder

CLIPImageEncoder is an image encoder that wraps the image embedding functionality using the CLIP

ImageBind

ImageBind One Embedding Space to Bind Them All

CLIP-API-service

CLIP as a service - Embed image and sentences, object recognition, visual reasoning, image classification and reverse image search

Chinese-CLIP

Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.

Few-shot-NL2SQL-with-prompting

Matrix-Theory

电子科技大学《矩阵理论》复习笔记

ollama

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

RoCLIP

Robust Contrastive Language-Image Pretraining against Data Poisoning and Backdoor Attacks

CLIP4CMR

A Comprehensive Empirical Study of Vision-Language Pre-trained Model for Supervised Cross-Modal Retrieval

Adversarial-Prompt-Tuning

ECCV2024: Adversarial Prompt Tuning for Vision-Language Models

VLAttack

This is an official repository of ``VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models'' (NeurIPS 2023).