Text Classification
Transformers
Safetensors
English
roberta
customer-support
sentiment-analysis
lora
distillation
text-embeddings-inference
Instructions to use Grinding/ticketsense-category with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Grinding/ticketsense-category with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Grinding/ticketsense-category")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("Grinding/ticketsense-category") model = AutoModelForSequenceClassification.from_pretrained("Grinding/ticketsense-category") - Notebooks
- Google Colab
- Kaggle
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -12,12 +12,12 @@ tags:
|
|
| 12 |
- distillation
|
| 13 |
---
|
| 14 |
|
| 15 |
-
#
|
| 16 |
|
| 17 |
Fine-tuned `distilroberta-base` (82M params) for `category` classification on real
|
| 18 |
customer-support tweets, with labels distilled from **Claude Sonnet 4.6**.
|
| 19 |
|
| 20 |
-
Part of the [
|
| 21 |
specialized classifier that approximates frontier-LLM judgement at a fraction of
|
| 22 |
the cost and latency.
|
| 23 |
|
|
@@ -42,7 +42,7 @@ the cost and latency.
|
|
| 42 |
|
| 43 |
```python
|
| 44 |
from transformers import pipeline
|
| 45 |
-
clf = pipeline("text-classification", model="Grinding/
|
| 46 |
clf("my card was charged twice and nobody has responded")
|
| 47 |
```
|
| 48 |
|
|
|
|
| 12 |
- distillation
|
| 13 |
---
|
| 14 |
|
| 15 |
+
# TicketSense — Category Classifier
|
| 16 |
|
| 17 |
Fine-tuned `distilroberta-base` (82M params) for `category` classification on real
|
| 18 |
customer-support tweets, with labels distilled from **Claude Sonnet 4.6**.
|
| 19 |
|
| 20 |
+
Part of the [TicketSense](https://github.com/Genious07/ticketsense) project: a tiny
|
| 21 |
specialized classifier that approximates frontier-LLM judgement at a fraction of
|
| 22 |
the cost and latency.
|
| 23 |
|
|
|
|
| 42 |
|
| 43 |
```python
|
| 44 |
from transformers import pipeline
|
| 45 |
+
clf = pipeline("text-classification", model="Grinding/ticketsense-category")
|
| 46 |
clf("my card was charged twice and nobody has responded")
|
| 47 |
```
|
| 48 |
|