Sn Mpnet Base Snli Mnli

🚀 Siamese Network Model for Zero-Shot and Few-Shot Text Classification

This is a Siamese network model trained for zero-shot and few-shot text classification. It maps sentences and paragraphs to a 768-dimensional dense vector space, offering a powerful solution for text-related tasks.

🚀 Quick Start

Prerequisites

The base model is mpnet-base, and it was trained on SNLI and MNLI.

Model Features

• Sentence Embedding: It's a sentence-transformers model, capable of transforming sentences and paragraphs into 768-dimensional dense vectors.
• Versatile Use Cases: Suitable for zero-shot classification, sentence similarity, feature extraction, and more.

📦 Installation

To use this model, you need to install sentence-transformers. You can install it using the following command:

pip install -U sentence-transformers

💻 Usage Examples

Basic Usage with Sentence-Transformers

Once you have sentence-transformers installed, using the model is straightforward:

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 with HuggingFace Transformers

If you don't have sentence-transformers installed, you can still use the model. First, pass your input through the transformer model, and then apply the appropriate pooling operation on 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[0] #First element of model_output contains all token embeddings
    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 we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
model = AutoModel.from_pretrained('{MODEL_NAME}')

# 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, max pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])

print("Sentence embeddings:")
print(sentence_embeddings)

📚 Documentation

Model Information