metadata
license: mit
base_model: jhu-clsp/ettin-encoder-1b
library_name: onnx
pipeline_tag: feature-extraction
tags:
- code-search
- retrieval
- onnx
- anvesa
anvesa-code-1b
A code-search encoder for anvesa: Ettin-encoder-1b (jhu-clsp, MIT) fine-tuned
on 105 MIT-licensed repositories. ONNX, fp32: model.onnx with its weights in model.onnx_data, and
tokenizer.json. Mean pooling over real tokens, L2-normalised, 512 tokens, no prefix. It embeds anvesa's symbol
cards without their WQL path line.
ranker-noword.json is the XGBoost ranker fit on this encoder's scores for anvesa's experimental.learnedRanker
(20 features, no word overlap).
| corpus test (1,710 generated queries, 57 repos, 13 languages) | bench (241 hand-written queries, 8 repos) | |
|---|---|---|
| first stage, hub penalty 0.3 | 0.352 | 0.685 |
| with the ranker | 0.370 | 0.699 |
CPU: 373 ms a card (ONNX Runtime, 12 threads). For comparison, all-MiniLM-L6-v2 scores 0.293 and 0.547 without a ranker.
anvesa model install anvesa-code-1b --download