Instructions to use BlueOrangeDigital/distilbert-cross-segment-document-chunking with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BlueOrangeDigital/distilbert-cross-segment-document-chunking with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="BlueOrangeDigital/distilbert-cross-segment-document-chunking")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("BlueOrangeDigital/distilbert-cross-segment-document-chunking") model = AutoModelForSequenceClassification.from_pretrained("BlueOrangeDigital/distilbert-cross-segment-document-chunking") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -8,6 +8,8 @@ datasets:
|
|
| 8 |
- wikipedia
|
| 9 |
pipeline_tag: text-classification
|
| 10 |
base_model: "distilbert/distilbert-base-uncased"
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
# DistilBERT Cross Segment Document Chunking
|
|
|
|
| 8 |
- wikipedia
|
| 9 |
pipeline_tag: text-classification
|
| 10 |
base_model: "distilbert/distilbert-base-uncased"
|
| 11 |
+
widget:
|
| 12 |
+
- text: "Left context. [SEP] Right context."
|
| 13 |
---
|
| 14 |
|
| 15 |
# DistilBERT Cross Segment Document Chunking
|