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:

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

carles-undergrad-thesis/indobert-mmarco-margin-mse

This is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.

Usage (Sentence-Transformers)

Using this model becomes easy when you have sentence-transformers installed:

pip install -U sentence-transformers

Then you can use the model like this:

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

model = SentenceTransformer('carles-undergrad-thesis/indobert-mmarco-margin-mse')
embeddings = model.encode(sentences)
print(embeddings)

Usage (HuggingFace Transformers)

Without sentence-transformers, 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.

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/indobert-mmarco-margin-mse')
model = AutoModel.from_pretrained('carles-undergrad-thesis/indobert-mmarco-margin-mse')

# 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
$\text{IndoBERT}_{\text{DOTMargin}}$	.207	.799	.446	.929	.387	.899

Training

The model was trained with the parameters:

DataLoader:

torch.utils.data.dataloader.DataLoader of length 15717 with parameters:

{'batch_size': 32, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}

Loss:

beir.losses.margin_mse_loss.MarginMSELoss

Parameters of the fit()-Method:

{
    "epochs": 5,
    "evaluation_steps": 0,
    "evaluator": "NoneType",
    "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": 7858,
    "weight_decay": 0.01
}

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 256, '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})
)