metadata
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- causal-lm
license:
- cc-by-sa-4.0
TODO: Name of Model
TODO: Description
Model Description
TODO: Add relevant content
(0) Base Transformer Type: RobertaModel
(1) Pooling mean
Usage (Sentence-Transformers)
Using this model becomes more convenient 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"]
model = SentenceTransformer(TODO)
embeddings = model.encode(sentences)
print(embeddings)
Usage (HuggingFace Transformers)
from transformers import AutoTokenizer, AutoModel
import torch
# The next step is optional if you want your own pooling function.
# Max Pooling - Take the max value over time for every dimension.
def max_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
token_embeddings[input_mask_expanded == 0] = -1e9 # Set padding tokens to large negative value
max_over_time = torch.max(token_embeddings, 1)[0]
return max_over_time
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained(TODO)
model = AutoModel.from_pretrained(TODO)
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, max_length=128, return_tensors='pt'))
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, max pooling.
sentence_embeddings = max_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)