Imran1/embadding

Model using

from transformers import AutoConfig, AutoTokenizer
from torch import nn
import torch.nn.functional as F
import torch
# First, define your custom model class again
class HFCustomBertModel(nn.Module):
    def __init__(self, config):
        super().__init__()
        self.bert = BertModel(config)
        self.pooler = nn.Sequential(
            nn.Linear(config.hidden_size, config.hidden_size),
            nn.Tanh()
        )

    def forward(self, input_ids, attention_mask=None, token_type_ids=None):
        outputs = self.bert(input_ids, attention_mask=attention_mask, token_type_ids=token_type_ids)
        pooled_output = self.pooler(outputs.pooler_output)
        return pooled_output
def load_custom_model_and_tokenizer(model_path):
    # Load the config
    config = AutoConfig.from_pretrained(model_path)
    
    # Initialize the custom model with the config
    model = HFCustomBertModel(config)
    # Load the tokenizer
    tokenizer = AutoTokenizer.from_pretrained(model_path)
    
    return model, tokenizer

# Usage
model_path = "Imran1/embadding"  
model, tokenizer = load_custom_model_and_tokenizer(model_path)



queries = ["how much protein should a female eat"]
documents = ["As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or training for a marathon. Check out the chart below to see how much protein you should be eating each day."]

model.eval()  # Set the model to evaluation mode

with torch.no_grad():
    # Tokenize and encode the queries and documents
    query_inputs = tokenizer(queries, padding=True, truncation=True, return_tensors="pt")
    document_inputs = tokenizer(documents, padding=True, truncation=True, return_tensors="pt")
    
    # Get embeddings
    query_embeddings = model(**query_inputs)
    document_embeddings = model(**document_inputs)

    # Normalize embeddings
    query_embeddings = F.normalize(query_embeddings, p=2, dim=1)
    document_embeddings = F.normalize(document_embeddings, p=2, dim=1)

    # Calculate cosine similarity
    scores = torch.matmul(query_embeddings, document_embeddings.transpose(0, 1))

print(f"Similarity score: {scores.item():.4f}")
Similarity score: 0.9605