Views
No views yet
distilbert-base-uncased trained on real customer support tweets from the Customer Support on Twitter dataset.| ID | Label |
|---|---|
| 0 | Billing inquiry |
| 1 | Cancellation request |
| 2 | Product inquiry |
| 3 | Refund request |
| 4 | Technical issue |
| Metric | Value |
|---|---|
| Test Accuracy | 99.0% |
| Macro F1 | 0.989 |
| Training Time | ~4.5 min (T4 GPU) |
| Inference Latency | ~60ms (CPU) |
1from transformers import pipeline
2
3classifier = pipeline(
4 "text-classification",
5 model="abhimanyu345/ticket-classifier"
6)
7
8result = classifier("I was charged twice for my subscription this month")
9print(result)
10# [{'label': 'Billing inquiry', 'score': 0.9996}]1@misc{gupta2026ticketclassifier,
2 author = {Abhimanyu Gupta},
3 title = {Customer Support Ticket Classifier with MLOps Pipeline},
4 year = {2026},
5 publisher = {HuggingFace},
6 journal = {HuggingFace Model Hub},
7 howpublished = {\url{https://huggingface.co/abhimanyu345/ticket-classifier}}
8}