Describe the expanded retrieval model comparisons
Browse files
README.md
CHANGED
|
@@ -28,6 +28,6 @@ passages can repeat the same fact.
|
|
| 28 |
|
| 29 |
**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.
|
| 30 |
|
| 31 |
-
Each card has a runnable example near the top, its training recipe and a comparison with the exact upstream checkpoint
|
| 32 |
|
| 33 |
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.
|
|
|
|
| 28 |
|
| 29 |
**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.
|
| 30 |
|
| 31 |
+
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.
|
| 32 |
|
| 33 |
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.
|