gte-small-int8-dynamic

gte-small-int8-dynamic

This is thenlper/gte-small INT8 model quantized with huggingface/optimum-intel through the usage of Intel® Neural Compressor.

Usage

Below is an example to encode queries and passages from the MS-MARCO passage ranking dataset.

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer
from optimum.intel.neural_compressor import INCModel

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]

input_texts = [
  'how much protein should a female eat',
  'summit define',
  "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.",
  "Definition of summit for English Language Learners. : 1  the highest point of a mountain : the top of a mountain. : 2  the highest level. : 3  a meeting or series of meetings between the leaders of two or more governments."
]

model_name = "efederici/gte-small-int8-dynamic"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = INCModel.from_pretrained(model_name)

batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')
outputs = model(**batch_dict)
embeddings = average_pool(outputs.last_hidden_state, batch_dict['attention_mask'])

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

print(scores.tolist())