Skip to content
View gosoon's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report gosoon

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

《How to Scale Your Model》中文翻译项目 - 智能技术文档翻译工具。专为大语言模型扩展技术书籍设计,突破长文档翻译瓶颈,完美保留数学公式、代码块格式。采用占位符机制+分层翻译策略,基于Gemini API提供高质量翻译。Python+crawl4ai技术栈,支持批量处理和增量更新。

HTML 81 7 Updated Aug 30, 2025

Achieve state of the art inference performance with modern accelerators on Kubernetes

Shell 2,225 271 Updated Dec 19, 2025

Inference Llama 2 in one file of pure C

C 19,054 2,432 Updated Aug 6, 2024

本项目旨在分享大模型相关技术原理以及实战经验(大模型工程化、大模型应用落地)

HTML 22,530 2,635 Updated Dec 24, 2025

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

Python 3,810 290 Updated Dec 26, 2025

fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型,任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型,单并发20tps;INT4量化模型单并发30tps,多并发可达60+。

C++ 4,115 416 Updated Dec 4, 2025

校招、秋招、春招、实习好项目!带你从零实现一个高性能的深度学习推理库,支持大模型 llama2 、Unet、Yolov5、Resnet等模型的推理。Implement a high-performance deep learning inference library step by step

C++ 3,252 355 Updated Jun 22, 2025

博客配套视频链接: https://space.bilibili.com/383551518?spm_id_from=333.1007.0.0 b 站直接看 配套 github 链接:https://github.com/nickchen121/Pre-training-language-model 配套博客链接:https://www.cnblogs.com/nickchen121/p/1…

482 103 Updated Jul 12, 2022

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

Python 70,517 7,671 Updated Dec 27, 2025
Python 1,672 101 Updated Sep 30, 2025

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

Python 13,106 868 Updated Dec 17, 2024

基于Qwen2.5模型、使用DISC-Law-SFT-Pair数据集微调的法律大模型

Python 9 2 Updated Dec 29, 2024

Transformer 原理剖析与实践(从零开始)@月来客栈 出品

Python 10 2 Updated Mar 14, 2025

cuda从零实现transformer

Cuda 4 Updated Sep 25, 2025

🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT!🌏 Train a 26M-parameter GPT from scratch in just 2h!

Python 36,222 4,276 Updated Dec 26, 2025

这是一个从头训练大语言模型的项目,包括预训练、微调和直接偏好优化,模型拥有1B参数,支持中英文。

Python 710 94 Updated Feb 18, 2025

Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.

Python 51,115 4,243 Updated Dec 24, 2025

小红书笔记 | 评论爬虫、抖音视频 | 评论爬虫、快手视频 | 评论爬虫、B 站视频 | 评论爬虫、微博帖子 | 评论爬虫、百度贴吧帖子 | 百度贴吧评论回复爬虫 | 知乎问答文章|评论爬虫

Python 41,023 9,184 Updated Dec 26, 2025

Transformers 库快速入门教程

Python 1,788 213 Updated Sep 20, 2024
Jupyter Notebook 65 21 Updated Jul 13, 2025

llama3 implementation one matrix multiplication at a time

Jupyter Notebook 15,203 1,289 Updated May 23, 2024

从零实现一个 llama3 中文版

Jupyter Notebook 1,000 99 Updated Jun 12, 2024

Public repo for HF blog posts

Jupyter Notebook 3,273 958 Updated Dec 22, 2025

个人构建MoE大模型:从预训练到DPO的完整实践

Python 2,139 160 Updated Dec 16, 2025

Transformer的完整实现。详细构建Encoder、Decoder、Self-attention。以实际例子进行展示,有完整的输入、训练、预测过程。可用于学习理解self-attention和Transformer

Python 117 21 Updated Apr 10, 2025

深度学习经典、新论文逐段精读

32,242 2,765 Updated Mar 22, 2025

AI 基础知识 - GPU 架构、CUDA 编程、大模型基础及AI Agent 相关知识

HTML 666 110 Updated Dec 26, 2025

A high-throughput and memory-efficient inference and serving engine for LLMs

Python 66,306 12,229 Updated Dec 27, 2025
Next