Instructions to use vespa-engine/col-minilm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vespa-engine/col-minilm with Transformers:
# Load model directly from transformers import AutoTokenizer, ColBERT tokenizer = AutoTokenizer.from_pretrained("vespa-engine/col-minilm") model = ColBERT.from_pretrained("vespa-engine/col-minilm", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# MS Marco Ranking with ColBERT on Vespa.ai
|
| 2 |
|
| 3 |
Model is based on [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://arxiv.org/abs/2004.12832).
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
tags:
|
| 5 |
+
- search
|
| 6 |
+
- ranking
|
| 7 |
+
- vespa
|
| 8 |
+
license: mit
|
| 9 |
+
|
| 10 |
+
base_model: "cross-encoder/ms-marco-MiniLM-L-6-v2"
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
# MS Marco Ranking with ColBERT on Vespa.ai
|
| 14 |
|
| 15 |
Model is based on [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://arxiv.org/abs/2004.12832).
|