Commit 80610be

@@ -26,6 +26,16 @@ happening to your tokens. For GPU backends, real sampling, tool-calling, or
 broad architecture support, use
 [elelem-llama](https://src.mokhan.ca/elelem/llama) instead.
 
+Attention bias is optional and the output projection falls back to the tied
+token embedding when absent, so the loader also *loads* other dense
+architectures (e.g. Llama-family GGUFs) without crashing. It doesn't decode
+them correctly: RoPE ordering is architecture-dependent (Qwen2 needs NEOX,
+Llama-family needs NORMAL) and there's no GGUF metadata key that says which
+-- llama.cpp derives it from the architecture name, which would mean
+hardcoding a per-architecture branch. That's the line this gem doesn't
+cross, so only Qwen2-family models produce correct output. Verified by
+direct experiment; see `spec/elelem/ggml/provider_spec.rb`.
+
 See `spec/` for what's currently verified.
 
 ## Setup