Attach model card from MODEL_CARDS.md (LogReg Intent Classifier)

README.md

@@ -1,24 +1,14 @@
 ---
 license: apache-2.0
-base_model: google/embeddinggemma-300m
-library_name: sklearn
 tags:
-- conference-demo
-- local-ai
 - intent-classification
----
-
-**⚠️ Conference talk demo — not production weights.**
-
-This model accompanies a conference keynote on local on-device AI. Published
-as a reference for the fine-tuning patterns shown on stage — **not** a
-deployable artefact. No security audit, no SLA, pinned to the talk's state.
-
-- Source repository: [thinktecture-labs/local-multi-model-agent-slm](https://github.com/thinktecture-labs/local-multi-model-agent-slm)
-- Threat model + out-of-scope: [`SECURITY.md`](SECURITY.md)
-- Licensing details: [`MODEL_LICENSES.md`](MODEL_LICENSES.md)
-- All five models in the stack: [Collection — Local Multi-Model Agent — nextera fine-tunes](https://huggingface.co/collections/thinktecture/local-multi-model-agent-nextera-fine-tunes-6a04a8ff2a40e5696f3c2f18)
-
+- text-classification
+- logistic-regression
+- sklearn
+- conference-talk-demo
+language:
+- en
+library_name: sklearn
 ---
 
 ## LogReg Intent Classifier
@@ -27,13 +17,17 @@ deployable artefact. No security audit, no SLA, pinned to the talk's state.
 |---|---|
 | **Base** | scikit-learn `LogisticRegression`, multinomial, L2 penalty |
 | **License** | Apache-2.0 (this repo) — but inputs are EmbeddingGemma vectors so the [Gemma Terms](MODEL_LICENSES.md) cover the embedding step |
-| **Training script** | [`training/train_intent_logreg.py`](https://github.com/thinktecture-labs/local-multi-model-agent-slm/blob/main/training/train_intent_logreg.py) |
+| **Training script** | [`training/train_intent_logreg.py`](../training/train_intent_logreg.py) |
 | **Method** | LogReg on FT-EmbeddingGemma's 768-dim output vectors. Held-out 90/10 split. ~2 minutes on CPU. |
 | **Training data** | Same as Gemma3-1B intent: `data/training-data/gemma3_intent_{scenario}.jsonl` (re-embedded with the FT EmbeddingGemma) |
 | **Hardware** | CPU is sufficient. Requires the FT EmbeddingGemma llama-server running on port 9092/9096 to embed training examples. |
 | **Intended use** | Replaces the 1B generative classifier as the primary intent router. ~10ms per query (vs ~200ms for the 1B). Same accuracy on the standard eval set. |
-| **Out of scope** | Anything that requires generation (it's a 3-way classifier). Falls back to the 1B classifier when confidence is below threshold (defaults to 0.65). |
+| **Out of scope** | Anything that requires generation (it's a 3-way classifier). Low-confidence predictions (< 0.60 threshold, configurable in `intent_classifier_logreg.py`) are overridden to `direct_answer` as a safe fallback intent. The 1B generative classifier is only used as a load-time fallback when the LogReg model file is absent, not as a per-query confidence fallback. |
 | **Reference eval (Nextera)** | 96.1% on 180-query eval set. ~10ms per classification (single CPU thread). |
 | **Known failure modes** | When the EmbeddingGemma FT changes, the LogReg weights become invalid — `intent_classifier_logreg.py:13-15` warns about this coupling. Re-train both together. |
 
 ---
+
+Source repository: https://github.com/thinktecture-labs/local-multi-model-agent-slm
+
+Generated from `finetune/MODEL_CARDS.md` — see source repo for the full pipeline + reproducibility instructions.