msmarco-distilbert-dot-v5

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, 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-dot-v5')

# 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
print("Query:", query)
for doc, score in doc_score_pairs:
   print(score, doc)

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 correct pooling-operation on-top of the contextualized word embeddings.

from transformers import AutoTokenizer, AutoModel
import torch

# Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
   token_embeddings = model_output.last_hidden_state
   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)

# 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 = mean_pooling(model_output, encoded_input['attention_mask'])

   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-dot-v5")
model = AutoModel.from_pretrained("sentence-transformers/msmarco-distilbert-dot-v5")

# 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
print("Query:", query)
for doc, score in doc_score_pairs:
   print(score, doc)