128 lines
3.9 KiB
Markdown
128 lines
3.9 KiB
Markdown
---
|
|
pipeline_tag: sentence-similarity
|
|
license: apache-2.0
|
|
tags:
|
|
- sentence-transformers
|
|
- feature-extraction
|
|
- sentence-similarity
|
|
- transformers
|
|
---
|
|
|
|
# sentence-transformers/msmarco-distilbert-base-tas-b
|
|
|
|
This is a port of the [DistilBert TAS-B Model](https://huggingface.co/sebastian-hofstaetter/distilbert-dot-tas_b-b256-msmarco) to [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and is optimized for the task of semantic search.
|
|
|
|
|
|
|
|
## 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, util
|
|
|
|
query = "How many people live in London?"
|
|
docs = ["Around 9 Million people live in London", "London is known for its financial district"]
|
|
|
|
#Load the model
|
|
model = SentenceTransformer('sentence-transformers/msmarco-distilbert-base-tas-b')
|
|
|
|
#Encode query and documents
|
|
query_emb = model.encode(query)
|
|
doc_emb = model.encode(docs)
|
|
|
|
#Compute dot score between query and all document embeddings
|
|
scores = util.dot_score(query_emb, doc_emb)[0].cpu().tolist()
|
|
|
|
#Combine docs & scores
|
|
doc_score_pairs = list(zip(docs, scores))
|
|
|
|
#Sort by decreasing score
|
|
doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True)
|
|
|
|
#Output passages & scores
|
|
for doc, score in doc_score_pairs:
|
|
print(score, doc)
|
|
```
|
|
|
|
|
|
|
|
## 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
|
|
|
|
#CLS Pooling - Take output from first token
|
|
def cls_pooling(model_output):
|
|
return model_output.last_hidden_state[:,0]
|
|
|
|
#Encode text
|
|
def encode(texts):
|
|
# Tokenize sentences
|
|
encoded_input = tokenizer(texts, padding=True, truncation=True, return_tensors='pt')
|
|
|
|
# Compute token embeddings
|
|
with torch.no_grad():
|
|
model_output = model(**encoded_input, return_dict=True)
|
|
|
|
# Perform pooling
|
|
embeddings = cls_pooling(model_output)
|
|
|
|
return embeddings
|
|
|
|
|
|
# Sentences we want sentence embeddings for
|
|
query = "How many people live in London?"
|
|
docs = ["Around 9 Million people live in London", "London is known for its financial district"]
|
|
|
|
# Load model from HuggingFace Hub
|
|
tokenizer = AutoTokenizer.from_pretrained("sentence-transformers/msmarco-distilbert-base-tas-b")
|
|
model = AutoModel.from_pretrained("sentence-transformers/msmarco-distilbert-base-tas-b")
|
|
|
|
#Encode query and docs
|
|
query_emb = encode(query)
|
|
doc_emb = encode(docs)
|
|
|
|
#Compute dot score between query and all document embeddings
|
|
scores = torch.mm(query_emb, doc_emb.transpose(0, 1))[0].cpu().tolist()
|
|
|
|
#Combine docs & scores
|
|
doc_score_pairs = list(zip(docs, scores))
|
|
|
|
#Sort by decreasing score
|
|
doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True)
|
|
|
|
#Output passages & scores
|
|
for doc, score in doc_score_pairs:
|
|
print(score, doc)
|
|
```
|
|
|
|
|
|
|
|
## Evaluation Results
|
|
|
|
|
|
|
|
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/msmarco-distilbert-base-tas-b)
|
|
|
|
|
|
|
|
## Full Model Architecture
|
|
```
|
|
SentenceTransformer(
|
|
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: DistilBertModel
|
|
(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})
|
|
)
|
|
```
|
|
|
|
## Citing & Authors
|
|
|
|
Have a look at: [DistilBert TAS-B Model](https://huggingface.co/sebastian-hofstaetter/distilbert-dot-tas_b-b256-msmarco) |