ottoline/ottoline-sentiment-v3
Text classification125M paramssafetensorsLicense: apache-2.0en#sentiment#reviews
Updated Sep 17, 2026
Part of the Open Pace seed catalog. Weights are listed for the preview and become downloadable at launch.
Overview
Three-way sentiment for product reviews and support tickets, calibrated so the scores mean something.
ottoline/ottoline-sentiment-v3 is a 125M-parameter text classification model, published in safetensors under the apache-2.0 license.
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 ottoline/ottoline-sentiment-v3
# Python (planned)
from openpace import load
model = load("ottoline/ottoline-sentiment-v3")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 apache-2.0. Read the license file before using the weights commercially.