deep learning for image processing including classification and object-detection etc.

This repository is a collection of awesome things about vision prompts, including papers, code, etc.

AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning (ICLR 2023).

Federated Learning for LLMs.

A flexible Federated Learning Framework based on PyTorch, simplifying your Federated Learning research.

Ethereal Style for Zotero

Code for CVPR2023 DaFKD : Domain-aware Federated Knowledge Distillation

🦜🔗 Build context-aware reasoning applications

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

Implementation of "SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networks"

The official GitHub page for the survey paper "A Survey of Large Language Models".

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…

StableLM: Stability AI 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…

The official GitHub page for the survey paper "A Survey on Evaluation of Large Language Models".

Official github repo for C-Eval, a Chinese evaluation suite for foundation models [NeurIPS 2023]

中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard

This repository contains code from our paper Efficient and Accurate Conversion of Spiking Neural Network with Burst Spikes, published in IJCAI, 2022.

Benchmark of federated learning. Dedicated to the community. 🤗

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）

Acceptance rates for the major AI conferences

Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

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。

An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".