Lists (19)
Sort Name ascending (A-Z)
Book
Diffusion Model
扩散模型相关Fine-tuning
模型微调技巧General Embedding
文本表征模型Information Extraction
信息抽取相关项目Large Language Model
LLM Agent
LLM Annotation
基于大模型的数据标注LLM-based Data Annotation
LLM-based Information extraction
Music
🚀 My stack
NLP-Corpus
自然语言处理数据集NLP面试
NLP面试相关内容Python
Python相关项目Query纠错
Query纠错相关Synthetic Data Generation
合成数据生成Text To Speech
Tools
Stars
📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程
一个基于LLM的演示文稿生成平台,能够自动将文档内容转换为专业的PPT演示文稿。平台支持多种AI模型,提供丰富的模板和样式选择,让用户能够创建高质量的演示文稿。
欢迎来到电子书下载宝库,一个汇聚了各类电子书下载链接的地方。无论你是喜欢阅读经典文学、经管励志、终身学习、职场创业、技术手册还是其他类型的书籍,这里都能满足你的需求。 该库涵盖了帆书app(原樊登读书)、微信读书、京东读书、喜马拉雅等读书app的大部分电子书。
天池中药说明书实体识别挑战冠军方案;中文命名实体识别;NER; BERT-CRF & BERT-SPAN & BERT-MRC;Pytorch
nick-2008 / Time-MoE
Forked from Time-MoE/Time-MoE[ICLR 2025 Spotlight] Official implementation of "Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts"
Python implementation for fine-tuning and using Time-MoE time series foundation model. This repository contains tools for preprocessing data, fine-tuning TimeMoE-50M on custom datasets (optimized f...
[ICLR 2025 Spotlight] Official implementation of "Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts"
We discuss nonlinear model predictive control (NMPC) for multi-body dynamics via physics-informed machine learning methods. Physics-informed neural networks (PINNs) are a promising tool to approxim...
A fast and differentiable model predictive control (MPC) solver for PyTorch.
Turn your Python application into an Android APK
nanoGPT with Chinese annotation, for self learning.
Video+code lecture on building nanoGPT from scratch
Re-implementation of Andrej Karpathy's nanoGPT
The nanoGPT-style implementation of RWKV Language Model - an RNN with GPT-level LLM performance.
One-click training of your own GPT. Training a GPT has never been easier for beginners. / 一键预训练+SFT一个属于自己的LLM,0基础训练GPT原来可以这么简单?
本项目从零开始构建并优化了一个千万参数级别的大规模预训练语言模型,涵盖预训练、有监督微调(SFT)和R1推理蒸馏三个阶段。项目采用自定义Transformer架构(包括RMSNorm、分组注意力、多Query机制、SwiGLU激活和RoPE位置编码),实现高效的长文本处理和自回归生成。同时,开发了基于BBPE编码的分词器,针对中文进行了优化,构建了轻量级词表。预训练阶段通过混合精度训练、梯度...
LLM大模型开源的非常多,对于想深入了解transformer模型结构,从零开始完整训练一个大模型,不用推理框架使用模型推理往往无从入手,另外开源模型往往对gpu有一定要求,不利于新手深入探索,我们尝试解决这些问题
MambaStock: Selective state space model for stock prediction
Simple, minimal implementation of the Mamba SSM in one file of PyTorch.
A quickstart and benchmark for pytorch distributed training.
Automatically crawl arXiv papers daily and summarize them using AI. Illustrating them using GitHub Pages.
教育各种资料,从幼儿园到小学、中学,涵盖学而思,万维、猿辅导等多个机构,持续增加中
PyTorch implementation of "Effective Approaches to Attention-based Neural Machine Translation" using scheduled sampling to improve the parameter estimation process.
基于pytorch实现的时间序列预测训练框架,各个部分模块化,方便修改模型。包含时间序列预测模型、训练、验证、测试、可视化、onnx导出、onnx推理。
proof of concept for a transformer-based time series prediction model