Aarushhh
/

SEWY3-246M-untrained

Text Generation

Model card Files Files and versions

New custom modified architecture

Inspired by NanoGPT(by Keller Jordan)

Making the archetecture work using AutoModelForCausalLM still WIP

Downloads last month: 2

Safetensors

Model size

0.2B params

Tensor type

F32

·