倉庫議題
kyegomez/attn_res
A clean, single-file PyTorch implementation of Attention Residuals (Kimi Team, MoonshotAI, 2026), integrated with Grouped Query Attention (GQA), SwiGLU feed-forward networks, and Rotary Position Embeddings (RoPE).
議題
此倉庫沒有已關閉的已索引議題。