AI Native Data App Development framework with AWEL(Agentic Workflow Expression Language) and Agents

基于langchain+gradio搭建本地个人助理

Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM)

Question and Answer based on Anything.

Firefly(流萤): 中文对话式大语言模型(全量微调+QLoRA)，支持微调Mixtral-8x7B、Zephyr、Mistral、Aquila2、Baichuan2、CodeLlama、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya、Bloom等大模型

Extension of Langchain for RAG. Easy benchmarking, multiple retrievals, reranker, time-aware RAG, and so on...

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

Chinese and English multimodal conversational language model | 多模态中英双语对话语言模型

qwen-7b and qwen-14b finetuning

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.

Implementation of InstructEdit

Dataset, code and models for the paper "MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing".

Official implementation of the paper "Improving Sample Quality of Diffusion Models Using Self-Attention Guidance"

中国的Quant相关资源索引

本地知识库 + chatGLM6B + CustomAgent

Official Pytorch implementation for "Transferable Adversarial Attacks on Vision Transformers with Token Gradient Regularization" (CVPR 2023).

CVPR and NeurIPS poster examples and templates. May we have in-person poster session soon!

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

This repository contains the official code for the CVPR 2023 paper ``Adversarial Counterfactual Visual Explanations''

official PyTorch implement of Towards Adversarial Attack on Vision-Language Pre-training Models

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

The official code for T-SEA: Transfer-based Self-Ensemble Attack on Object Detection (CVPR2023) Resources

[NeurIPS 2022] A official PyTorch implementation of PTv2, also a codebase for point cloud recognition research.

Raising the Cost of Malicious AI-Powered Image Editing

Official repository for "Boosting Adversarial Transferability using Dynamic Cues " (ICLR 2023)

A new adversarial purification method that uses the forward and reverse processes of diffusion models to remove adversarial perturbations.