File size: 1,878 Bytes
1abaa49 078820f 1abaa49 078820f |
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 |
---
license: apache-2.0
language:
- en
pipeline_tag: text-classification
tags:
- url
- urls
- classification
---
This is a very small version of BERT, intended for later fine-tune under URL analysis.
An updated version of the old basic model for URL analysis
Old version: https://huggingface.co/CrabInHoney/urlbert-tiny-base-v2
Model size
3.69M params
Tensor type
F32
Test example:
from transformers import BertTokenizerFast, BertForMaskedLM, pipeline
import torch
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
print(f"Используемое устройство: {device}")
model_name = "CrabInHoney/urlbert-tiny-base-v3"
tokenizer = BertTokenizerFast.from_pretrained(model_name)
model = BertForMaskedLM.from_pretrained(model_name)
model.to(device)
fill_mask = pipeline(
"fill-mask",
model=model,
tokenizer=tokenizer,
device=0 if torch.cuda.is_available() else -1
)
sentences = [
"http://example.[MASK]/"
]
for sentence in sentences:
print(f"\nИсходное предложение: {sentence}")
results = fill_mask(sentence)
for result in results:
token_str = result['token_str']
score = result['score']
print(f"Предсказанное слово: {token_str}, вероятность: {score:.4f}")
Output:
Исходное предложение: http://example.[MASK]/
Предсказанное слово: com, вероятность: 0.7018
Предсказанное слово: org, вероятность: 0.1191
Предсказанное слово: nl, вероятность: 0.0406
Предсказанное слово: net, вероятность: 0.0294
Предсказанное слово: ca, вероятность: 0.0190 |