NanoGPT (124M) in 90 seconds

pytorch-tiny-imagenet

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Low-bit optimizers for PyTorch

Deep neural network framework for multiple GPUs

Accessible large language models via k-bit quantization for PyTorch.

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

Official implementation of ICML 2024 paper "ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking".

Skyformer: Remodel Self-Attention with Gaussian Kernel and Nystr\"om Method (NeurIPS 2021)

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

KarSein for CTR predict

The official implementation of Ada2Fair (RecSys'24 Short Paper).

[KDD 2026] FCN: Fusing Exponential and Linear Cross Network for Click-Through Rate Prediction

Official PyTorch implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States

[KDD 2024] This is the official PyTorch implementation for the paper: "Rotative Factorization Machines"

Long Range Arena for Benchmarking Efficient Transformers

ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.

Repository hosting code for "Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations" (https://arxiv.org/abs/2402.17152).

[KDD 2024] This is the official PyTorch implementation for the paper: "Rotative Factorization Machines"

Code for ACM RecSys 2023 paper "Turning Dross Into Gold Loss: Is BERT4Rec really better than SASRec?"

A comprehensive library for implementing LLMs, including a unified training pipeline and comprehensive model evaluation.

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…

Scripts for processing the Amazon Reviews 2023 dataset; implementations and checkpoints of BLaIR: "Bridging Language and Items for Retrieval and Recommendation".

Benchmarks for classification of genomic sequences

Official implementation for HyenaDNA, a long-range genomic foundation model built with Hyena

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)