My learning notes for ML SYS.

SGLang is a fast serving framework for large language models and vision language models.

Official Implementation of "Learning Harmonized Representations for Speculative Sampling" (HASS)

Build, evaluate and train General Multi-Agent Assistance with ease

Official repository for the paper "LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code"

A self-learning tutorail for CUDA High Performance Programing.

Fully open reproduction of DeepSeek-R1

10W首中文歌词数据库

The most comprehensive database of Chinese poetry 🧶最全中华古诗词数据库, 唐宋两朝近一万四千古诗人, 接近5.5万首唐诗加26万宋诗. 两宋时期1564位词人，21050首词。

Code and documentation to train Stanford's Alpaca models, and generate the data.

A collection of open-source dataset to train instruction-following LLMs (ChatGPT,LLaMA,Alpaca)

InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions

Code for "Learning to summarize from human feedback"

chatglm-6b微调/LORA/PPO/推理, 样本为自动生成的整数/小数加减乘除运算, 可gpu/cpu

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

GLM (General Language Model)

Python module to decode/encode Geohashes to/from latitude and longitude. See http://en.wikipedia.org/wiki/Geohash

微信小程序商城，微信小程序微店

[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer

Stable Diffusion web UI

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

SD-Trainer. LoRA & Dreambooth training scripts & GUI use kohya-ss's trainer, for diffusion model.

AUTOMATIC1111 Stable Diffusion WebUI 1.5 + Kohya's Scripts

Pytorch implementation of CosFace

投胎模拟器

chinese version of longformer

Open Chinese Language Pre-trained Model Zoo

基于BERT的预训练语言模型实现，分为两步：预训练和微调。目前已包括BERT、Roberta、ALbert三个模型，且皆可支持Whole Word Mask模式。

An Inplementation of CRF (Conditional Random Fields) in PyTorch 1.0