Downloads · 30 days
30
25% of all-time downloads
late_interaction
polodealvarado/late_interaction
late_interaction is a zero-shot classification model from polodealvarado. Use it when you need labels you did not train the model on. It is set up for transformers. The card lists the license as mit.
ColBERT-style token-level MaxSim scoring for fine-grained alignment.
All-time downloads
118
Public
Parameters
110M
438 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors438 MB · 100%
At a glance
- Task
- Zero-Shot Classification
- Library
- transformers
- License
- mit
- Access
- Public
- Created
- Mar 1, 2026
- Updated
- Mar 1, 2026
- SHA
- 0bfd487d
Try a prompt
Base models
Model card
From the Hugging Face model README
Zero-Shot Text Classification — late_interaction
ColBERT-style token-level MaxSim scoring for fine-grained alignment.
This model encodes texts and candidate labels into a shared embedding space using BERT, enabling classification into arbitrary categories without retraining for new labels.
Training Details
| Parameter | Value |
|---|---|
| Base model | bert-base-uncased |
| Model variant | late_interaction |
| Training steps | 1000 |
| Batch size | 2 |
| Learning rate | 2e-05 |
| Trainable params | 109,580,672 |
| Training time | 354.7s |
Dataset
Trained on polodealvarado/zeroshot-classification.
Evaluation Results
| Metric | Score |
|---|---|
| Precision | 0.8546 |
| Recall | 0.9686 |
| F1 Score | 0.9081 |
Usage
from models.late_interaction import LateInteractionModel
model = LateInteractionModel.from_pretrained("polodealvarado/late_interaction")
predictions = model.predict(
texts=["The stock market crashed yesterday."],
labels=[["Finance", "Sports", "Biology", "Economy"]],
)
print(predictions)
# [{"text": "...", "scores": {"Finance": 0.98, "Economy": 0.85, ...}}]
- Task
- Zero-Shot Classification
- Library
- transformers
- License
- mit
- Languages
- en
- Created
- Mar 1, 2026
- Updated
- Mar 1, 2026