Show each retrieval model’s contribution to the pipeline

README.md

@@ -1,33 +1,33 @@
----
-title: Daecore
-sdk: static
-emoji: 📚
-colorFrom: gray
-colorTo: blue
----
-
-# Small models for local search and passage labeling
-
-Daecore's models find and organize evidence in working notes and technical documentation. They run locally through ONNX Runtime, without a hosted model API, and each package can be used on its own.
-
-| Model | Use it to | Returns | License |
-|---|---|---|---|
-| [EmbeddingGemma 300M v2](https://huggingface.co/Daecore/embeddinggemma-300m-memory-ft-v2) | Find passages related to a query | A normalized 768-dimensional vector per query or passage | Gemma Terms of Use |
-| [Ettin 150M](https://huggingface.co/Daecore/ettin-150m-memory-reranker-ft-v1) | Put the most useful candidates first | A relevance score per query–passage pair | Apache-2.0 |
+---
+title: Daecore
+sdk: static
+emoji: 📚
+colorFrom: gray
+colorTo: blue
+---
+
+# Small models for local search and passage labeling
+
+Daecore's models find and organize evidence in working notes and technical documentation. They run locally through ONNX Runtime, without a hosted model API, and each package can be used on its own.
+
+| Model | Use it to | Returns | License |
+|---|---|---|---|
+| [EmbeddingGemma 300M v2](https://huggingface.co/Daecore/embeddinggemma-300m-memory-ft-v2) | Find passages related to a query | A normalized 768-dimensional vector per query or passage | Gemma Terms of Use |
+| [Ettin 150M](https://huggingface.co/Daecore/ettin-150m-memory-reranker-ft-v1) | Put the most useful candidates first | A relevance score per query–passage pair | Apache-2.0 |
 | [GLiClass Knowledge Classifier v2](https://huggingface.co/Daecore/gliclass-knowledge-classifier-v2) | Label what a passage contains | Scores for trap, decision, constraint, mechanism and procedure | Apache-2.0 |
-
-**Retrieval.** Gemma and Ettin form Daecore's retrieval pipeline. Gemma and BM25 keyword search retrieve candidates, reciprocal-rank fusion merges their rankings, and Ettin reranks up to 50 unique passages. A calibrated selector then returns 3–20 of them when enough candidates exist.
-
-Passages are prepared before retrieval: deterministic structural chunking
-follows headings and natural boundaries, carries section context, and keeps
-code and table framing where possible. Token-aware splitting bounds oversized
-material. Training uses frozen snapshots of these passages, including earlier
-parser outputs; changing the chunker changes the evidence available to search.
-Results are source passages for an agent to read and use, and several relevant
-passages can repeat the same fact.
-
-**Passage labeling.** GLiClass serves a separate Daecore function: labeling what a passage contains, so stored material can be organized by kind. It is not a retrieval component and needs neither retrieval model; its labels do not judge relevance, truth or authority.
-
-Each card has a runnable example near the top, its training recipe and a comparison with the exact upstream checkpoint on Daecore's evaluation data. Gemma also reports five public retrieval datasets and the storage/quality tradeoff of smaller embeddings; Ettin reports two public reranking datasets. Their cards share a clearly separate full-pipeline results table.
-
-Task-specific training and evaluation rely on mostly generated organizational documents and model-generated labels, without a human-adjudicated reference, so reported gains describe that data rather than a general improvement over the upstream models. Serving checks ran on one Windows x64 machine with an NVIDIA RTX 3060 Ti; Linux and AMD or Intel GPUs are untested.
+
+**Retrieval.** Gemma and Ettin form Daecore's retrieval pipeline. Gemma and BM25 keyword search retrieve candidates, reciprocal-rank fusion merges their rankings, and Ettin reranks up to 50 unique passages. A calibrated selector then returns 3–20 of them when enough candidates exist.
+
+Passages are prepared before retrieval: deterministic structural chunking
+follows headings and natural boundaries, carries section context, and keeps
+code and table framing where possible. Token-aware splitting bounds oversized
+material. Training uses frozen snapshots of these passages, including earlier
+parser outputs; changing the chunker changes the evidence available to search.
+Results are source passages for an agent to read and use, and several relevant
+passages can repeat the same fact.
+
+**Passage labeling.** GLiClass serves a separate Daecore function: labeling what a passage contains, so stored material can be organized by kind. It is not a retrieval component and needs neither retrieval model; its labels do not judge relevance, truth or authority.
+
+Each card has a runnable example near the top, its training recipe and a comparison with the exact upstream checkpoint on Daecore's evaluation data. Gemma also reports five public retrieval datasets and the storage/quality tradeoff of smaller embeddings; Ettin reports two public reranking datasets. Their pipeline tables change one model at a time against the same fully fine-tuned system, showing what each contributes alongside BM25.
+
+Task-specific training and evaluation rely on mostly generated organizational documents and model-generated labels, without a human-adjudicated reference, so reported gains describe that data rather than a general improvement over the upstream models. Serving checks ran on one Windows x64 machine with an NVIDIA RTX 3060 Ti; Linux and AMD or Intel GPUs are untested.