paraphrase Mini L M L6 v2

Introduction

The paraphrase-MiniLM-L6-v2 model is a sentence-transformers model that converts sentences and paragraphs into 384-dimensional dense vector spaces. It is suitable for tasks such as clustering and semantic search.

Architecture

The model architecture is a SentenceTransformer consisting of a Transformer layer and a Pooling layer. The Transformer is based on a BertModel with a maximum sequence length of 128 tokens. The pooling layer uses mean pooling to aggregate token embeddings into sentence embeddings.

Training

The model was trained by the sentence-transformers team, as outlined in the paper "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks" by Reimers and Gurevych.

Guide: Running Locally

To run this model locally, you can use either the sentence-transformers library or the Hugging Face Transformers library.

Using Sentence-Transformers

1. Install the library:

   pip install -U sentence-transformers
   

2. Use the model:

   from sentence_transformers import SentenceTransformer
   
   sentences = ["This is an example sentence", "Each sentence is converted"]
   model = SentenceTransformer('sentence-transformers/paraphrase-MiniLM-L6-v2')
   embeddings = model.encode(sentences)
   print(embeddings)
   

Using Hugging Face Transformers

1. Install necessary packages:

   pip install transformers torch
   

2. Use the model:

   from transformers import AutoTokenizer, AutoModel
   import torch
   
   # Define mean pooling function
   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('sentence-transformers/paraphrase-MiniLM-L6-v2')
   model = AutoModel.from_pretrained('sentence-transformers/paraphrase-MiniLM-L6-v2')
   
   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)
   

For better performance, consider using cloud GPUs such as AWS EC2, GCP, or Azure.

License

The paraphrase-MiniLM-L6-v2 model is licensed under the Apache 2.0 License.