Document GGUF files: base-model-only, needs patched llama.cpp, raw-completion usage

USAGE.md

@@ -54,3 +54,26 @@ The **base** is a base model: fluent, drifts, loops — post-train it.
 The **adapters** are small hand-made SFT stages over ~1,031 human-written examples;
 see the model card for their personalities. This is a 1B: charming, honest about
 what it doesn't know, and not a reasoning engine. 12×7 may not be 84. That's the deal.
+
+## GGUF (llama.cpp)
+
+Two GGUF conversions of the **base** pretrain checkpoint (not the `lora.py` chat adapters — those aren't merged in) are provided under `gguf/`:
+
+| File | Size | Use |
+|---|---|---|
+| `gguf/tessera-1b-Q6_K.gguf` | ~883 MB | recommended — Q6_K quant, ~6.6 bits/weight |
+| `gguf/tessera-1b-f16.gguf` | ~2.2 GB | full-precision source, requantize to other sizes from this |
+
+### Important: requires a patched llama.cpp build
+
+ProtoGPT uses **RMSNorm** (see `model.py`), but llama.cpp's stock `gpt2` architecture — the correct match for everything else here (learned absolute position embeddings, GELU MLP, fused-QKV full attention, no biases) — hard-codes classic mean-centered LayerNorm. **A GGUF built for this model will not load correctly on unpatched/upstream llama.cpp, Ollama, LM Studio, or any other tool bundling stock llama.cpp** — it'll run without erroring but compute the wrong norm.
+
+`tessera1b-rmsnorm-gpt2-arch.patch` is included in this repo: a 6-line diff against `llama.cpp/src/models/gpt2.cpp` that swaps the 3 `build_norm(..., LLM_NORM, ...)` call sites to `LLM_NORM_RMS` and makes the (unused, always-zero) norm bias tensors optional. Apply it to a fresh llama.cpp checkout, rebuild, then use that binary for both `llama-quantize` and inference.
+
+### Usage — raw completion, not chat
+
+This is a base model. Use `llama-completion` (plain next-token continuation), not `llama-cli`'s interactive/conversation mode — that auto-applies a chat template (ChatML by default) this model was never trained on and produces garbage as a result.
+
+```
+./llama-completion -m tessera-1b-Q6_K.gguf -p "Your prompt here" -n 100 --temp 0.3
+```