Downloads · 30 days
15
28% of all-time downloads
2026-24679-studyspots-distilbert
CXu0630/2026-24679-studyspots-distilbert
2026-24679-studyspots-distilbert is a text classification model from CXu0630. Use it when you need a label for a piece of text. It is set up for transformers.
Fine-tuned distilbert-base-uncased predicting whether a short campus review recommends the study spot it describes (1) or not (0).
All-time downloads
53
Public
Parameters
67M
268 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors268 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- distilbert
- Access
- Public
- Created
- Sep 23, 2026
- Updated
- Sep 23, 2026
- SHA
- ba1e371b
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
Study-Spot Recommendation Classifier (DistilBERT)
Fine-tuned distilbert-base-uncased predicting whether a short campus review recommends
the study spot it describes (1) or not (0).
Source data
Fine-tuned on ssg1/study-spots-text, a classmate-built
text dataset for 24-679 (Fall 2026), Carnegie Mellon University. Trained on the prepared train
split (including augmented reviews); model selection used the unaugmented validation split.
Test results (15 original reviews)
| Metric | Value |
|---|---|
| Accuracy | 0.867 |
| Balanced accuracy | 0.875 |
| Precision (recommended) | 0.778 |
| Recall (recommended) | 1.000 |
| F1 (recommended) | 0.875 |
2 of 15 test reviews were misclassified; see the training notebook for the per-example error analysis.
Intended use and limitations
Classroom exercise (24-679). A small, non-random sample of two campuses' study spots; not validated as a general sentiment classifier.
Load
from transformers import pipeline
classifier = pipeline("text-classification", model="CXu0630/2026-24679-studyspots-distilbert")
classifier("Way too loud to get any real work done.")
- Task
- Text Classification
- Library
- transformers
- Type
- distilbert
- Created
- Sep 23, 2026
- Updated
- Sep 23, 2026