45 lines
1.7 KiB
Markdown
45 lines
1.7 KiB
Markdown
---
|
|
language:
|
|
- de
|
|
tags:
|
|
- cross-encoder
|
|
widget:
|
|
- text: Was sind Lamas. Das Lama (Lama glama) ist eine Art der Kamele. Es ist in den
|
|
südamerikanischen Anden verbreitet und eine vom Guanako abstammende Haustierform.
|
|
example_title: Example Query / Paragraph
|
|
license: apache-2.0
|
|
metrics:
|
|
- Rouge-Score
|
|
library_name: sentence-transformers
|
|
pipeline_tag: text-ranking
|
|
---
|
|
# cross-encoder-mmarco-german-distilbert-base
|
|
|
|
## Model description:
|
|
This model is a fine-tuned [cross-encoder](https://www.sbert.net/examples/training/cross-encoder/README.html) on the [MMARCO dataset](https://huggingface.co/datasets/unicamp-dl/mmarco) which is the machine translated version of the MS MARCO dataset.
|
|
As base model for the fine-tuning we use [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased)
|
|
|
|
Model input samples are tuples of the following format, either
|
|
`<query, positive_paragraph>` assigned to 1 or `<query, negative_paragraph>` assigned to 0.
|
|
|
|
The model was trained for 1 epoch.
|
|
|
|
## Model usage
|
|
The cross-encoder model can be used like this:
|
|
|
|
```
|
|
from sentence_transformers import CrossEncoder
|
|
model = CrossEncoder('model_name')
|
|
scores = model.predict([('Query 1', 'Paragraph 1'), ('Query 2', 'Paragraph 2')])
|
|
```
|
|
|
|
The model will predict scores for the pairs `('Query 1', 'Paragraph 1')` and `('Query 2', 'Paragraph 2')`.
|
|
|
|
For more details on the usage of the cross-encoder models have a look into the [Sentence-Transformers](https://www.sbert.net/)
|
|
|
|
## Model Performance:
|
|
Model evaluation was done on 2000 evaluation paragraphs of the dataset.
|
|
|
|
| Accuracy | F1-Score | Precision | Recall |
|
|
| --- | --- | --- | --- |
|
|
| 89.70 | 86.82 | 86.82 | 93.50 | |