---
datasets:
- glue
model-index:
- name: contriever-mnli
  results: []
pipeline_tag: zero-shot-classification
language:
- en
license: mit
---

# contriever-mnli

This model is a fine-tuned version of [facebook/contriever](https://huggingface.co/facebook/contriever) on the glue dataset.

## Model description

[Unsupervised Dense Information Retrieval with Contrastive Learning](https://arxiv.org/abs/2112.09118).
Gautier Izacard, Mathilde Caron, Lucas Hosseini, Sebastian Riedel, Piotr Bojanowski, Armand Joulin, Edouard Grave, arXiv 2021

## How to use the model

The model can be loaded with the `zero-shot-classification` pipeline like so:

```python
from transformers import pipeline
classifier = pipeline("zero-shot-classification",
                      model="mjwong/contriever-mnli")
```

You can then use this pipeline to classify sequences into any of the class names you specify.

```python
sequence_to_classify = "one day I will see the world"
candidate_labels = ['travel', 'cooking', 'dancing']
classifier(sequence_to_classify, candidate_labels)
#{'sequence': 'one day I will see the world',
# 'labels': ['travel', 'cooking', 'dancing'],
# 'scores': [0.7728410363197327, 0.13207288086414337, 0.09508601576089859]}
```

If more than one candidate label can be correct, pass `multi_class=True` to calculate each class independently:

```python
candidate_labels = ['travel', 'cooking', 'dancing', 'exploration']
classifier(sequence_to_classify, candidate_labels, multi_class=True)
#{'sequence': 'one day I will see the world',
# 'labels': ['exploration', 'travel', 'cooking', 'dancing'],
# 'scores': [0.9920766353607178,
#  0.7247188091278076,
#  0.08411424607038498,
3  0.03875880688428879]}
```

### Eval results
The model was evaluated using the dev sets for MultiNLI and test sets for ANLI. The metric used is accuracy.

|Datasets|mnli_dev_m|mnli_dev_mm|anli_test_r1|anli_test_r2|anli_test_r3|
| :---: | :---: | :---: | :---: | :---: | :---: |
|[contriever-mnli](https://huggingface.co/mjwong/contriever-mnli)|0.821|0.822|0.247|0.281|0.312|
|[contriever-msmarco-mnli](https://huggingface.co/mjwong/contriever-msmarco-mnli)|0.820|0.819|0.244|0.296|0.306|

### Training hyperparameters

The following hyperparameters were used during training:

- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5

### Framework versions
- Transformers 4.28.1
- Pytorch 1.12.1+cu116
- Datasets 2.11.0
- Tokenizers 0.12.1