ChenHuaYou
Follow
Starred repositories
Ready-to-use SRT / WebRTC / RTSP / RTMP / LL-HLS media server and media proxy that allows to read, publish, proxy, record and playback video and audio streams.
Empowering RAG with a memory-based data interface for all-purpose applications!
Groq QA is a CLI tool and Python library for generating question-answer pairs from text, featuring custom train/test dataset split ratios and the ability to upload directly to Hugging Face for fine…
2025年2月更新，目前国内可用Docker镜像源汇总，DockerHub国内镜像加速列表，🚀DockerHub镜像加速器
RAG-QA-Generator 是一个用于检索增强生成（RAG）系统的自动化知识库构建与管理工具。该工具通过读取文档数据，利用大规模语言模型生成高质量的问答对（QA对），并将这些数据插入数据库中，实现RAG系统知识库的自动化构建和管理。
AirLLM 70B inference with single 4GB GPU
Use PEFT or Full-parameter to finetune 450+ LLMs (Qwen2.5, InternLM3, GLM4, Llama3.3, Mistral, Yi1.5, Baichuan2, DeepSeek-R1, ...) and 150+ MLLMs (Qwen2.5-VL, Qwen2-Audio, Llama3.2-Vision, Llava, I…
Fast and accurate automatic speech recognition (ASR) for edge devices
DSPy: The framework for programming—not prompting—language models
[NeurIPS 2024] Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image
A Blender extension for an easy-to-use remesher that outputs good-quality quad topology
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Personal pipeline for batch retargeting kinematic motions (BVH) between different skeletons with the help of Auto-Rig Pro in Blender.
🌞 CareGPT (关怀GPT)是一个医疗大语言模型，同时它集合了数十个公开可用的医疗微调数据集和开放可用的医疗大语言模型，包含LLM的训练、测评、部署等以促进医疗LLM快速发展。Medical LLM, Open Source Driven for a Healthy Future.
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO、GRPO。
This repository contains the implementation of a facings identifier using YOLOv8 and image embeddings. The goal of this project is to count the number of facings (product instances) of each product…
Define mesh-based VFX in RON files and load them into bevy
A Shadertoy clone for the Bevy game engine. The glsl language is replaced by wgsl.
Real-time wgsl visualisation tooling for educating oneself in the art of shader programming
Template for a Bevy game including CI/CD for web, Windows, Linux, macOS, iOS and Android
第一个支持中英文双语语音-文本多模态对话的开源可商用对话模型。便捷的语音输入将大幅改善以文本为输入的大模型的使用体验，同时避免了基于 ASR 解决方案的繁琐流程以及可能引入的错误。
A plugin for bevy which allows you to create screens to show the brands and development teams behind your amazing game