#大语言模型#Fault-tolerant, highly scalable GPU orchestration, and a machine learning framework designed for training models with billions to trillions of parameters
MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.
Guide: Finetune GPT2-XL (1.5 Billion Parameters) and finetune GPT-NEO (2.7 B) on a single GPU with Huggingface Transformers using DeepSpeed
This repo contains the data preparation, tokenization, training and inference code for BLOOMChat. BLOOMChat is a 176 billion parameter multilingual chat model based on BLOOM.
ModuleFormer is a MoE-based architecture that includes two different types of experts: stick-breaking attention heads and feedforward experts. We released a collection of ModuleFormer-based Language M...
#计算机科学#DeepSpeed Chat: 一键式RLHF训练,让你的类ChatGPT千亿大模型提速省钱15倍
[ICCV 2025] Official repo for "GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation"
Xaddress - Give 7 billion people an instant physical address
Framework for evaluating ANNS algorithms on billion scale datasets.
Solutions to the "7 Billion Humans" challenges
Neat URL cleans URLs, removing parameters such as Google Analytics' utm parameters.
Pretrained language model with 100B parameters
1️⃣🐝🏎️ The One Billion Row Challenge - .NET Edition
Formerly known as code.google.com/p/1-billion-word-language-modeling-benchmark
#博客#Some information about parameters and options available in COLMAP - SfM & MVS software. https://colmap.github.io
Zoomable, animated scatterplots in the browser that scales over a billion points
PyTorch Language Model for 1-Billion Word (LM1B / GBW) Dataset
Hidden parameters discovery suite