-
Guilin University Of Electronic Technology
- Guilin, Guangxi, China
Highlights
- Pro
Lists (1)
Sort Name ascending (A-Z)
Stars
c/c++ webrtc native janus client Qt opengl video-meeting video-room video-call text-room meeting chat
每个人都能看懂的大模型知识分享,LLMs春/秋招大模型面试前必看,让你和面试官侃侃而谈
✔(已完结)最全面的 深度学习 笔记【土堆 Pytorch】【李沐 动手学深度学习】【吴恩达 深度学习】
《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调(全参数/Lora)、部署国内外开源大模型(LLM)/多模态大模型(MLLM)教程
适用于所有大语言模型,使所有模型具备类似response-format的能力。帮助用户解析模型并生成引导提示词(Response format Prompt),使大模型严格按照要求的JSON格式来输出,并提供方法实现数据从非结构化的文本转换到结构化的实例对象。
调用大模型已经是如今做 ai 项目习以为常的工作的,但是大模型的输出很多时候是不可控的,我们又需要使用大模型去做各种下游任务,实现可控可解析的输出。我们探索了一种和 python 开发可以紧密合作的开发方法。
[ECCV2024] Grounded Multimodal Large Language Model with Localized Visual Tokenization
lightweight, standalone C++ inference engine for Google's Gemma models.
这是一份入门AI/LLM大模型的逐步指南,包含教程和演示代码,带你从API走进本地大模型部署和微调,代码文件会提供Kaggle或Colab在线版本,即便没有显卡也可以进行学习。项目中还开设了一个小型的代码游乐场🎡,你可以尝试在里面实验一些有意思的AI脚本。同时,包含李宏毅 (HUNG-YI LEE)2024生成式人工智能导论课程的完整中文镜像作业。
Cross-platform, customizable multimedia/video processing framework. With strong GPU acceleration, heterogeneous design, multi-language support, easy to use, multi-framework compatible and high perf…
A library for high performance deep learning inference on NVIDIA GPUs.
TNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile、desktop and server. TNN is distinguished by several outstanding features, including its…
🚀 Easier & Faster YOLO Deployment Toolkit for NVIDIA 🛠️
Deep Learning API and Server in C++14 support for PyTorch,TensorRT, Dlib, NCNN, Tensorflow, XGBoost and TSNE
Implementation of popular deep learning networks with TensorRT network definition API
Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.
Machine Vision for NVIDIA Jetson. GPU accelerated video capture and neural networks for real-time object detection.
The TensorRT Inference Server provides a cloud inferencing solution optimized for NVIDIA GPUs.
A new tensorrt integrate. Easy to integrate many tasks
Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
Service Discovery & Load Balancing service implementation using UDP broadcasting and TCP
TCP/HTTP/UDP/QUIC client/server with Reactor over Netty
A QUIC client, client library and server implementation in Java. Supports HTTP3 with "Flupke" add-on.