Instructions to use SZLHOLDINGS/miniembed-nano-r1-candidate with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use SZLHOLDINGS/miniembed-nano-r1-candidate with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("SZLHOLDINGS/miniembed-nano-r1-candidate") sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
MiniEmbed-Nano r1 candidate (PROPOSAL-ONLY, measured candidate)
Status: proposal-only candidate. This is a real, trained sentence-transformers embedder intended to replace the SZLHOLDINGS/MiniEmbed-Nano hash-table fixture (64x12 SHA-256 table, not neural, never a real embedder) for the szl-skills research-memory retrieval role. The fixture repo is NOT overwritten; this is a separate candidate repo. Do not wire this into any skill until a human accepts it.
Measured eval (this run only; see eval_report.json)
Held-out slice of the two training corpora, group-split by source file so no eval chunk shares a source group with any training pair. Weak labels: chunk title as query, chunk text as positive. Binary relevance, shared corpus.
| metric | miniembed-r1 candidate | BM25 lexical baseline |
|---|---|---|
| nDCG@10 | 0.608145 | 0.527441 |
| recall@1 | 0.528986 | 0.460145 |
| recall@5 | 0.644928 | 0.554348 |
| recall@10 | 0.702899 | 0.597826 |
Eval size: 276 queries over 276 held-out chunks. This is title-query recall on two SZL corpora only β not an MTEB score and not evidence of general retrieval quality.
Provenance
- Base:
sentence-transformers/all-MiniLM-L6-v2@1110a243fdf4706b3f48f1d95db1a4f5529b4d41 - Data:
SZLHOLDINGS/szl-second-brain-inrepo+SZLHOLDINGS/rag-corpus-v1(titles -> chunk text, weak labels, seeded split); rejected: frontier-candidates (handles-only) and a11oy-verifiable-corpus (receipt logs) - Training pairs sha256 (pairs.train.jsonl):
22adee30dadd02111732a89511750219331f60e458dad91852503cceda4a4c0f - Seed 20260721, 2 epochs, batch 32, lr 2e-05, MultipleNegativesRankingLoss, final train loss 0.843704
- Trained 2026-11-05T02:02:21.837202+00:00 UTC on
hf jobs uv run(flavor t4-small recommended)
Honesty
| Claim | Label |
|---|---|
| Neural embedder trained by SGD | TRUE (this candidate) |
| nDCG@10 / recall@{1,5,10} above | MEASURED (held-out, in-run) |
| Beats BM25 nDCG@10 on this slice | MEASURED TRUE |
| General-purpose retrieval quality | UNAVAILABLE |
| MTEB numbers | NONE PASTED |
| Overwrites MiniEmbed-Nano | FALSE β separate candidate repo |
Energy UNAVAILABLE. Trained by szl-estate/jobs/train_miniembed.py.
- Downloads last month
- 22
Model tree for SZLHOLDINGS/miniembed-nano-r1-candidate
Base model
nreimers/MiniLM-L6-H384-uncased