Serega6678's picture
Update README.md
3e8a16a
|
raw
history blame
1.31 kB
metadata
license: mit
language:
  - en
  - fr
  - de
  - it
  - es
  - pt
  - pl
  - nl
  - ru
pipeline_tag: token-classification
inference: false
tags:
  - mBERT
  - BERT
  - generic
  - entity-recognition

Model

The multilingual BERT finetunned on an artificially annotated multilingual subset of Oscar dataset. This model provides domain & language independent embedding for Entity Recognition Task.

Usage

Embeddings can be used out of the box or fine-tuned on specific datasets.

Get embeddings:

import torch
import transformers


model = transformers.AutoModel.from_pretrained(
    'numind/entity-recognition-general-sota-v1',
    output_hidden_states=True,
)
tokenizer = transformers.AutoTokenizer.from_pretrained(
    'numind/entity-recognition-general-sota-v1',
)

text = [
    "NuMind is an AI company based in Paris and USA.",
    "See other models from us on https://huggingface.co/numind"
]
encoded_input = tokenizer(
    text,
    return_tensors='pt',
    padding=True,
    truncation=True
)
output = model(**encoded_input)

# for better quality
emb = torch.cat(
    (output.hidden_states[-1], output.hidden_states[-7]),
    dim=2
)

# for better speed
# emb = output.hidden_states[-1]