đ dense_encoder-msmarco-distilbert-word2vec256k
This model is based on msmarco-word2vec256000-distilbert-base-uncased with a 256k sized vocabulary initialized with word2vec. It can be used for tasks like sentence similarity, clustering, or semantic search.
đ Quick Start
Prerequisites
You need to install sentence-transformers
to use this model easily:
pip install -U sentence-transformers
Basic Usage
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('{MODEL_NAME}')
embeddings = model.encode(sentences)
print(embeddings)
⨠Features
- Based on Specific Model: This model is based on msmarco-word2vec256000-distilbert-base-uncased with a 256k sized vocabulary initialized with word2vec.
- Trained on MS MARCO: It has been trained on MS MARCO using MarginMSELoss.
- High Performance:
- MS MARCO dev: 34.51 (MRR@10)
- TREC-DL 2019: 66.12 (nDCG@10)
- TREC-DL 2020: 68.62 (nDCG@10)
đĻ Installation
If you haven't installed sentence-transformers
, you can use the following command:
pip install -U sentence-transformers
đģ Usage Examples
Basic Usage (Sentence-Transformers)
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('{MODEL_NAME}')
embeddings = model.encode(sentences)
print(embeddings)
Advanced Usage (HuggingFace Transformers)
from transformers import AutoTokenizer, AutoModel
import torch
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0]
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
sentences = ['This is an example sentence', 'Each sentence is converted']
tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
model = AutoModel.from_pretrained('{MODEL_NAME}')
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
with torch.no_grad():
model_output = model(**encoded_input)
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
đ Documentation
Evaluation Results
For an automated evaluation of this model, see the Sentence Embeddings Benchmark: https://seb.sbert.net
Training
The model was trained with the following parameters:
DataLoader:
torch.utils.data.dataloader.DataLoader
of length 7858 with parameters:
{'batch_size': 64, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
Loss:
sentence_transformers.losses.MarginMSELoss.MarginMSELoss
Parameters of the fit()-Method:
{
"epochs": 30,
"evaluation_steps": 0,
"evaluator": "NoneType",
"max_grad_norm": 1,
"optimizer_class": "<class 'transformers.optimization.AdamW'>",
"optimizer_params": {
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 1000,
"weight_decay": 0.01
}
Full Model Architecture
SentenceTransformer(
(0): Transformer({'max_seq_length': 250, 'do_lower_case': False}) with Transformer model: DistilBertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
đ§ Technical Details
This model is based on the msmarco-word2vec256000-distilbert-base-uncased
model, which has a 256k sized vocabulary initialized with word2vec. It is trained on the MS MARCO dataset using MarginMSELoss
. The training process involves specific parameters for the DataLoader
, Loss
, and the fit()
method, which are detailed in the "Training" section. The model architecture consists of a Transformer
layer followed by a Pooling
layer.
đ License
No license information provided in the original document.