pisces365

OmniDrive

Qwen2-VL

Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

lerobot

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

CLIP-Adapter

Tip-Adapter

lora-pytorch

Simple but robust implementation of LoRA for PyTorch. Compatible with NLP, CV, and other model types. Strongly typed and tested.

nd-Mamba2-torch

Only implemented through torch: "bi - mamba2" , "vision- mamba2 -torch". support 1d/2d/3d/nd and support export by jit.script/onnx;

cobra

Cobra: Extending Mamba to Multi-modal Large Language Model for Efficient Inference

AI-Scientist

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

InjectGUI

macOS Integrated Injection Framework (GUI version)

rknn-toolkit2

clapper

Clapper.app, a video synthesizer and sequencer designed for the age of AI cinema

metahuman-stream

Real time interactive streaming digital human

Chinese-CLIP

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

rknn-toolkit2

Real-time-translation-typing

实时打字翻译软件、语音实时打字、语音实时翻译、LOL 语音打字

VAD

[ICCV 2023] VAD: Vectorized Scene Representation for Efficient Autonomous Driving

GraphRAG-Ollama-UI

GraphRAG-Ollama-UI + GraphRAG4OpenWebUI 融合版（有gradio webui配置生成RAG索引，有fastapi提供RAG API服务）

CF-Workers-docker.io

这个项目是一个基于 Cloudflare Workers 的 Docker 镜像代理工具。它能够中转对 Docker 官方镜像仓库的请求，解决一些访问限制和加速访问的问题。

gpt4free

The official gpt4free repository | various collection of powerful language models

lancedb

Developer-friendly, serverless vector database for AI applications. Easily add long-term memory to your LLM apps!

graphrag

A modular graph-based Retrieval-Augmented Generation (RAG) system

DB-GPT

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

ollama

Get up and running with Llama 3.2, Mistral, Gemma 2, and other large language models.

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Qwen2.5

Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.

free_chatgpt_api

🔥 公益免费的ChatGPT API，Free ChatGPT API，GPT4 API，可直连，无需代理，使用标准 OpenAI APIKEY 格式访问 ChatGPT，可搭配ChatGPT-next-web、ChatGPT-Midjourney、Lobe-chat、Botgem、FastGPT、沉浸式翻译等项目使用

mmdetection3d

OpenMMLab's next-generation platform for general 3D object detection.

DAIR-V2X

GD-MAE

GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Clouds (CVPR 2023)