ghLcd9dG

DiffPure

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

detoxify

Trained models & code to predict toxic comments on all 3 Jigsaw Toxic Comment Challenges. Built using ⚡ Pytorch Lightning and 🤗 Transformers. For access to our API, please email us at contact@unitary.ai.

AutoGPTQ

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

LLaVA-NeXT

diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.

Fatigue-Detection

Eye state classification using OpenCV and DLib to estimate Percentage Eye Closure (PERCLOS) and alert a drowsy person (such as a driver).

stablediffusion

High-Resolution Image Synthesis with Latent Diffusion Models

open-llms

📋 A list of open LLMs available for commercial use.

PurpleLlama

Set of tools to assess and improve LLM security.

FastGPT

FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letting you easily develop and deploy complex question-answering systems without the need for extensive setup or configuration.

Awesome-Multimodal-Large-Language-Models

:sparkles::sparkles:Latest Advances on Multimodal Large Language Models

MSR_20_Code_vulnerability_CSV_Dataset

A C/C++ Code Vulnerability Dataset with Code Changes and CVE Summaries

FakeLocation

Fake Location

tiny-gpu

A minimal GPU design in Verilog to learn how GPUs work from the ground up

Llama-Chinese

Llama中文社区，Llama3在线体验和微调模型已开放，实时汇总最新Llama3学习资料，已将所有代码更新适配Llama3，构建最好的中文Llama大模型，完全开源可商用

ChatGLM2-6B

ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型

LearnDeepSpeed

DeepSpeed教程 & 示例注释 & 学习笔记 （大模型高效训练）

PytorchNetHub

项目注释+论文复现+算法竞赛+Pytorch实践

Dromedary

Dromedary: towards helpful, ethical and reliable LLMs.

facefusion

Next generation face swapper and enhancer

llama-recipes

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.

llama3-Chinese-chat

Llama3、Llama3.1 中文仓库（随书籍撰写中... 各种网友及厂商微调、魔改版本有趣权重 & 训练、推理、评测、部署教程视频 & 文档）

EmoLLM

心理健康大模型、LLM、The Big Model of Mental Health、Finetune、InternLM2、InternLM2.5、Qwen、ChatGLM、Baichuan、DeepSeek、Mixtral、LLama3、GLM4、Qwen2、LLama3.1

dockerized

🐳 Build once, run anywhere

FaceBoxes

FaceBoxes: A CPU Real-time Face Detector with High Accuracy, IJCB, 2017

geektime-books

:books: 极客时间电子书

llama3

The official Meta Llama 3 GitHub site

codellama

Inference code for CodeLlama models

ChatDev

Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)

chinese-llm-benchmark

中文大模型能力评测榜单：目前已囊括106个大模型，覆盖chatgpt、gpt4o、百度文心一言、阿里通义千问、讯飞星火、商汤senseChat、minimax等商用模型， 以及百川、qwen2、glm4、yi、书生internLM2、llama3等开源大模型，多维度能力评测。不仅提供能力评分排行榜，也提供所有模型的原始输出结果！