di37/gemma3-270M-tinystories-pytorch
A complete PyTorch implementation of Google's Gemma3 270M language model, featuring sliding window attention, RoPE positional encoding, and efficient training infrastructure.
正在读取项目信息…
A complete PyTorch implementation of Google's Gemma3 270M language model, featuring sliding window attention, RoPE positional encoding, and efficient training infrastructure.