Decoder Only Transformer Pytorch

Inkling Ships: Murati’s Lab Puts Largest US Open-Weight AI on Hugging Face

Thinking Machines Lab Inkling launches as the largest US-built open-weight AI model — a 975-billion-parameter multimodal ...

GitHub

A Modular GPT Training Framework for Resource-Constrained Model Scaling

This repository presents a modular implementation of a decoder-only GPT (Generative Pre-trained Transformer) language model developed using PyTorch. The framework is designed to support reproducible ...

GitHub

EdgeGPT — Laptop-scale, Llama-compatible decoder-only transformer built in PyTorch. Train a small LLM from scratch and deploy to phone via llama.cpp + GGUF.

There was an error while loading. Please reload this page.

Some results have been hidden because they may be inaccessible to you

Show inaccessible results

Inkling Ships: Murati’s Lab Puts Largest US Open-Weight AI on Hugging Face

A Modular GPT Training Framework for Resource-Constrained Model Scaling

EdgeGPT — Laptop-scale, Llama-compatible decoder-only transformer built in PyTorch. Train a small LLM from scratch and deploy to phone via llama.cpp + GGUF.

Trending now