llama-models 0.1.1

Model architectures (Llama/Qwen/Mistral blocks) for llama.rs
Documentation

llama-models

Foundational model blocks for llama.rs:

  • RMSNorm
  • RoPE
  • Attention (scaled dot-product, single-step decode form)
  • MLP (SwiGLU)
  • Safetensors weight loading