Jesse-marqo's picture
Update README.md
eb26513 verified
metadata
license: apache-2.0

Rank-tuned e5-large-v2 on the Marqo-GS-10M dataset for ecommerce. Full details here https://github.com/marqo-ai/GCL

import torch.nn.functional as F

from torch import Tensor
from transformers import AutoTokenizer, AutoModel


def average_pool(last_hidden_states: Tensor,
                 attention_mask: Tensor) -> Tensor:
    last_hidden = last_hidden_states.masked_fill(~attention_mask[..., None].bool(), 0.0)
    return last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None]


# Each input text should start with "query: " or "passage: ".
# For tasks other than retrieval, you can simply use the "query: " prefix.
input_texts = ['query: Espresso Pitcher with Handle',
               'query: Women’s designer handbag sale',
               "passage: Dianoo Espresso Steaming Pitcher, Espresso Milk Frothing Pitcher Stainless Steel",
               "passage: Coach Outlet Eliza Shoulder Bag - Black - One Size"]

tokenizer = AutoTokenizer.from_pretrained('Marqo/marqo-gcl-e5-large-v2-130')
model_new = AutoModel.from_pretrained('Marqo/marqo-gcl-e5-large-v2-130')

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=77, padding=True, truncation=True, return_tensors='pt')

outputs = model_new(**batch_dict)
embeddings = average_pool(outputs.last_hidden_state, batch_dict['attention_mask'])

# normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:2] @ embeddings[2:].T) * 100
print(scores.tolist())