tidepool/tide-rerank-base

Overview

A cross-encoder that rescores search candidates. Pairs well with tide-embed-small.

tidepool/tide-rerank-base is a 280M-parameter text classification model, published in safetensors under the mit license. It builds on tidepool/tide-embed-small.

Intended use

• Text classification in en.
• Research, prototypes and products that keep a person in the loop.
• Fine-tuning as a starting point for a narrower task.

How to use

# Command-line client (planned; the shape may change)
pace pull tidepool/tide-rerank-base

# Python (planned)
from openpace import load
model = load("tidepool/tide-rerank-base")

Limitations

• It can state wrong things fluently. Check facts that matter.
• Quality drops on languages and domains that were thin in its training data.
• It reflects biases present in public text.

License

Released under mit. Read the license file before using the weights commercially.