muvon/octomind-rerank

Fine-tuned MS-MARCO MiniLM-L-6 cross-encoder (22M params, English) for octomind capability auto-activation. Designed as the second stage after the muvon/octomind-embed bi-encoder retrieves the top-N candidates.

Trained with BinaryCrossEntropyLoss over (anchor, positive) and (anchor, hard_negative) pairs from the octomind-tap catalog. The hard negatives target the confusable neighbors the bi-encoder alone cannot reliably separate.

Use

Wired into octomind via octolib's HuggingFace reranker provider (candle backend).

Downloads last month
44
Safetensors
Model size
0.3B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for muvon/octomind-rerank