You can deploy this model and start earning money today!

latent-lab/
neg-sp-en-trans-truth-qwen2.5-1.5b

Name: neg-sp-en-trans-truth-qwen2.5-1.5b
Availability: InStock

Views

No views yet

lmprobe: Linear Probe on Qwen2.5-1.5B

Truth probe for negated Spanish-English translation statements. Perfect accuracy (100%) — negation + translation knowledge fully intact at 1.5B scale.

Classes

0: false_statement
1: true_statement

Usage

python

from lmprobe import LinearProbe

probe = LinearProbe.from_hub("latent-lab/neg-sp-en-trans-truth-qwen2.5-1.5b", trust_classifier=True)
predictions = probe.predict(["your text here"])

Probe Details

Base model: Qwen/Qwen2.5-1.5B
Model revision: 8faed761d45a263340a0528343f099c05c9a4323
Layers: all (0–27, 28 layers)
Pooling: last_token
Classifier: logistic_regression
Task: classification
Random state: 42

Evaluation

Metric	Value
accuracy	1.0000
auroc	1.0000
f1	1.0000
precision	1.0000
recall	1.0000

Training Data

Positive examples: 141
Negative examples: 141
Positive hash: sha256:75c3a45288958ffea7d92153a65dd0b79987b4b3857243060cac05d26bbce1be
Negative hash: sha256:1d4e375735e1e6832841acb53e23eb56a7248628d01c15853646c81bababb04e
Evaluation samples: 72
Evaluation hash: sha256:242bd9b29e690cf82935955fa0cc3f0a06ec0b29317f0243f9068d83ebe0c83e

Reproducibility

lmprobe version: 0.5.8
Python: 3.12.3
PyTorch: 2.10.0+cu128
scikit-learn: 1.8.0
transformers: 5.3.0