Reranker

This tutorial is available as an IPython notebook at Malaya/example/reranker.

This module trained on both standard and local (included social media) language structures, so it is save to use for both.

import os

os.environ['CUDA_VISIBLE_DEVICES'] = ''
os.environ['TF_FORCE_GPU_ALLOW_GROWTH'] = 'true'

import logging

logging.basicConfig(level=logging.INFO)

%%time
import malaya

/home/husein/.local/lib/python3.8/site-packages/bitsandbytes/cextension.py:34: UserWarning: The installed version of bitsandbytes was compiled without GPU support. 8-bit optimizers, 8-bit multiplication, and GPU quantization are unavailable.
  warn("The installed version of bitsandbytes was compiled without GPU support. "

/home/husein/.local/lib/python3.8/site-packages/bitsandbytes/libbitsandbytes_cpu.so: undefined symbol: cadam32bit_grad_fp32
CPU times: user 3.22 s, sys: 2.61 s, total: 5.84 s
Wall time: 2.92 s

/home/husein/dev/malaya/malaya/tokenizer.py:214: FutureWarning: Possible nested set at position 3397
  self.tok = re.compile(r'({})'.format('|'.join(pipeline)))
/home/husein/dev/malaya/malaya/tokenizer.py:214: FutureWarning: Possible nested set at position 3927
  self.tok = re.compile(r'({})'.format('|'.join(pipeline)))

string1 = 'Pemuda mogok lapar desak kerajaan prihatin isu iklim'
string2 = 'Perbincangan isu pembalakan perlu babit kerajaan negeri'
string3 = 'kerajaan perlu kisah isu iklim, pemuda mogok lapar'
string4 = 'Kerajaan dicadang tubuh jawatankuasa khas tangani isu alam sekitar'

news1 = 'Tun Dr Mahathir Mohamad mengakui pembubaran Parlimen bagi membolehkan pilihan raya diadakan tidak sesuai dilaksanakan pada masa ini berikutan isu COVID-19'
tweet1 = 'DrM sembang pilihan raya tak boleh buat sebab COVID 19'

List available HuggingFace models

malaya.reranker.available_huggingface

{'mesolitica/reranker-malaysian-mistral-64M-32k': {'Size (MB)': 95.7,
  'Suggested length': 32768},
 'mesolitica/reranker-malaysian-mistral-191M-32k': {'Size (MB)': 332,
  'Suggested length': 32768},
 'mesolitica/reranker-malaysian-mistral-474M-32k': {'Size (MB)': 884,
  'Suggested length': 32768}}

Load HuggingFace model

def huggingface(
    model: str = 'mesolitica/reranker-malaysian-mistral-64M-32k',
    force_check: bool = True,
    **kwargs,
):
    """
    Load HuggingFace model for reranking task.

    Parameters
    ----------
    model: str, optional (default='mesolitica/reranker-malaysian-mistral-64M-32k')
        Check available models at `malaya.reranker.available_huggingface`.
    force_check: bool, optional (default=True)
        Force check model one of malaya model.
        Set to False if you have your own huggingface model.

    Returns
    -------
    result: malaya.torch_model.huggingface.Reranker
    """

model = malaya.reranker.huggingface()

Sort batch of strings

def sort(self, left_string: str, right_strings: List[str]):
    """
    Sort the strings.

    Parameters
    ----------
    left_string: str
        reference string.
    right_strings: List[str]
        query strings, list of strings need to sort based on reference string.

    Returns
    -------
    result: np.array
    """

v = model.sort(string1, [string1, string2, string3, string4, tweet1, news1])
v.shape

(6,)

v

array([ 6.898162 ,  5.124153 ,  4.9817924,  4.0060225, -8.165119 ,
       -1.5455011], dtype=float32)