---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers

---

This model utilizes a newer version of Sentence Transformers. If you're having trouble using this model, please try installing the latest version of Sentence Transformers with:

```bash
pip install --upgrade --force-reinstall --no-deps git+https://github.com/UKPLab/sentence-transformers.git
```

# carles-undergrad-thesis/st-indobert-mmarco-v1

This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.

<!--- Describe your model here -->

## Usage (Sentence-Transformers)

Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:

```
pip install -U sentence-transformers
```

Then you can use the model like this:

```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]

model = SentenceTransformer('carles-undergrad-thesis/st-indobert-mmarco-v1')
embeddings = model.encode(sentences)
print(embeddings)
```



## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.

```python
from transformers import AutoTokenizer, AutoModel
import torch


def cls_pooling(model_output, attention_mask):
    return model_output[0][:,0]


# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('carles-undergrad-thesis/st-indobert-mmarco-v1')
model = AutoModel.from_pretrained('carles-undergrad-thesis/st-indobert-mmarco-v1')

# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')

# Compute token embeddings
with torch.no_grad():
    model_output = model(**encoded_input)

# Perform pooling. In this case, cls pooling.
sentence_embeddings = cls_pooling(model_output, encoded_input['attention_mask'])

print("Sentence embeddings:")
print(sentence_embeddings)
```



## Evaluation Results


| Model                                   | Mmarco Dev |                | MrTyDi Test |                | Miracal Test |                            |
|-----------------------------------------|------------|----------------|-------------|----------------|--------------|----------------------------|
|                                         | MRR@10     | R@1000         | MRR@10      | R@1000         | NCDG@10      | R@1K                       | 
| $\text{BM25 (Elastic Search)}$          | .114       | .642           | .279        | .858           | .391         | .971                       |
| $\text{IndoBERT}_{\text{DOT}}$          | .192       | .847           | .378        | .936           | .355         | .920                       |



## Training
The model was trained with the parameters:

**DataLoader**:

`torch.utils.data.dataloader.DataLoader` of length 8325 with parameters:
```
{'batch_size': 64, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```

**Loss**:

`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
  ```
  {'scale': 1.0, 'similarity_fct': 'dot_score'}
  ```

Parameters of the fit()-Method:
```
{
    "epochs": 5,
    "evaluation_steps": 5000,
    "evaluator": "sentence_transformers.evaluation.SequentialEvaluator.SequentialEvaluator",
    "max_grad_norm": 1,
    "optimizer_class": "<class 'transformers.optimization.AdamW'>",
    "optimizer_params": {
        "correct_bias": false,
        "eps": 1e-06,
        "lr": 2e-05
    },
    "scheduler": "WarmupLinear",
    "steps_per_epoch": null,
    "warmup_steps": 4162,
    "weight_decay": 0.01
}
```


## Full Model Architecture
```
SentenceTransformer(
  (0): Transformer({'max_seq_length': 350, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False})
)
```

## Citing & Authors

<!--- Describe where people can find more information -->