File size: 4,153 Bytes
886800d d4d9982 ce78d29 674da47 4dcea13 2bf7408 438f7c9 4dcea13 438f7c9 4dcea13 438f7c9 3649e3b 0c5fc46 3649e3b 0c5fc46 4cee226 0c5fc46 2519c95 323990f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 |
---
license: unlicense
language:
- ru
tags:
- PyTorch
- e-commerce
- transformers.js
pipeline_tag: fill-mask
widget:
- text: электроника зарядка [MASK] USB
library_name: transformers
---
A model for solving the problem of missing words in search queries. The model uses the context of the query to generate possible words that could be missing.
```python
## don't forget
# pip install protobuf sentencepiece
from transformers import pipeline
unmasker = pipeline("fill-mask", model="fkrasnov2/COLD2", device="cuda")
unmasker("электроника зарядка [MASK] USB")
[{'score': 0.3712620437145233,
'token': 1131,
'token_str': 'автомобильная',
'sequence': 'электроника зарядка автомобильная usb'},
{'score': 0.12239563465118408,
'token': 7436,
'token_str': 'быстрая',
'sequence': 'электроника зарядка быстрая usb'},
{'score': 0.046715956181287766,
'token': 5819,
'token_str': 'проводная',
'sequence': 'электроника зарядка проводная usb'},
{'score': 0.031308457255363464,
'token': 635,
'token_str': 'универсальная',
'sequence': 'электроника зарядка универсальная usb'},
{'score': 0.02941182069480419,
'token': 2371,
'token_str': 'адаптер',
'sequence': 'электроника зарядка адаптер usb'}]
```
Coupled prepositions can be used to improve tokenization.
```python
unmasker("одежда женское [MASK] для_праздника")
[{'score': 0.9355553984642029,
'token': 503,
'token_str': 'платье',
'sequence': 'одежда женское платье для_праздника'},
{'score': 0.011321154423058033,
'token': 615,
'token_str': 'кольцо',
'sequence': 'одежда женское кольцо для_праздника'},
{'score': 0.008672593161463737,
'token': 993,
'token_str': 'украшение',
'sequence': 'одежда женское украшение для_праздника'},
{'score': 0.0038903721142560244,
'token': 27100,
'token_str': 'пончо',
'sequence': 'одежда женское пончо для_праздника'},
{'score': 0.003703165566548705,
'token': 453,
'token_str': 'белье',
'sequence': 'одежда женское белье для_праздника'}]
```
## For transformers.js, it turned out that the ONNX version of the model was required.
```python
from transformers import AutoTokenizer
from optimum.onnxruntime import ORTModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained("fkrasnov2/COLD2")
model = ORTModelForMaskedLM.from_pretrained("fkrasnov2/COLD2", file_name='model.onnx')
```
## You can also run and use the model straight from your browser.
```
index.html
```
```html
<!DOCTYPE html>
<html lang="ru">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Mask fill</title>
<link rel="stylesheet" href="styles.css">
<script src="main.js" type="module" defer></script>
</head>
<body>
<div class="container">
<textarea id="long-text-input" placeholder="Enter search query with [MASK]"></textarea>
<button id="generate-button">
Заполнить маску
</button>
<div id="output-div"></div>
</div>
</body>
</html>
```
```
main.js
```
```javascript
import { pipeline } from 'https://cdn.jsdelivr.net/npm/@huggingface/[email protected]';
const longTextInput = document.getElementById('long-text-input');
const output = document.getElementById('output-div');
const generateButton = document.getElementById('generate-button');
const pipe = await pipeline(
'fill-mask', // task
'fkrasnov2/COLD2' // model
);
generateButton.addEventListener('click', async () => {
const input = longTextInput.value;
const result = await pipe(input);
output.innerHTML = result[0].sequence;
output.style.display = 'block';
});
```
|