YaRN: Efficient Context Window Extension of Large Language Models

Example models using DeepSpeed

A series of large language models developed by Baichuan Intelligent Technology

Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models

The world's simplest facial recognition api for Python and the command line

Easy and Efficient Finetuning LLMs. (Supported LLama, LLama2, LLama3, Qwen, Baichuan, GLM , Falcon) 大模型高效量化训练+部署.

ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型

A large-scale 7B pretraining language model developed by BaiChuan-Inc.

Easy-to-use and powerful LLM and SLM library with awesome model zoo.

An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

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

为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…

Instruct-tune LLaMA on consumer hardware

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

An Open-Source Framework for Prompt-Learning.

LlamaIndex is the leading document agent and OCR platform

A TensorFlow Implementation of the Transformer: Attention Is All You Need

深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为18个章节，50余万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系scutjy2015@163.com 版权所有，违权必究 Tan 2018.06

🎨 《重学Java设计模式》是一本互联网真实案例实践书籍。以落地解决方案为核心，从实际业务中抽离出，交易、营销、秒杀、中间件、源码等22个真实场景，来学习设计模式的运用。欢迎关注小傅哥，微信(fustack)，公众号：bugstack虫洞栈，博客：https://bugstack.cn

Representation learning on large graphs using stochastic graph convolutions.

《统计学习方法》的代码实现

Tensorflow implementation of attention mechanism for text classification tasks.

Implementation and experiments of graph embedding algorithms.deep walk,LINE(Large-scale Information Network Embedding),node2vec,SDNE(Structural Deep Network Embedding),struc2vec

Implementation and experiments of graph embedding algorithms.

An Open-Source Package for Network Embedding (NE)

Implementation of Graph Convolutional Networks in TensorFlow

CodeHub is an iOS application written using Xamarin