Upload README.md with huggingface_hub

README.md

@@ -235,5 +235,15 @@ than merely declared.
 
 ## Other formats
 
-- [`ProCreations/auto-0.4b-gguf`](https://huggingface.co/ProCreations/auto-0.4b-gguf) — llama.cpp
 - [`ProCreations/auto-0.4b-ONNX`](https://huggingface.co/ProCreations/auto-0.4b-ONNX) — ONNX + int8
+
+The GGUF build was **withdrawn**. llama.cpp converts the model, but its `--pooling rank` path
+returns zero for a 2-class classification head, so the GGUF could not actually make
+approve/deny decisions — it returned identical `0.000` scores for a `rm -rf /` and for a
+`pytest` invocation. It was removed rather than left up implying it worked.
+
+## Successor
+
+[`ProCreations/auto-1b`](https://huggingface.co/ProCreations/auto-1b) scores **96.40%** on the
+same benchmark (vs 90.13% here), with false-deny down from 10.88% to 3.19% and long-context
+accuracy up from 78.45% to 97.02%. Prefer it unless you specifically need the smaller model.