README.md

metadata

license: apache-2.0
language:
  - zh
pipeline_tag: text-classification
library_name: transformers

risk-model-zh-v0.1

Introduction

This is a BERT model fine-tuned on a high-quality Chinese financial dataset. It generates a security risk score, which helps to identify and remove data with security risks from financial datasets, thereby reducing the proportion of illegal or undesirable data. For the complete data cleaning process, please refer to YiZhao.

Quickstart

Here is an example code snippet for generating security risk scores using this model.

import torch
from datasets import load_dataset
from transformers import AutoTokenizer, AutoModelForSequenceClassification

model_name = "risk-model-zh-v0.1"
dataset_file = "your_dataset.jsonl"
text_column = "text"
output_file = "your_output.jsonl"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name, torch_dtype=torch.bfloat16)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)

dataset = load_dataset('json', data_files=dataset_file, cache_dir="cache/", split='train', num_proc=12)


def compute_scores(batch):
    inputs = tokenizer(batch[text_column], return_tensors="pt", padding="longest", truncation=True).to(device)
    with torch.no_grad():
        outputs = model(**inputs)
        logits = outputs.logits.squeeze(-1).float().cpu().numpy()

    batch["risk_score"] = logits.tolist()
    return batch


dataset = dataset.map(compute_scores, batched=True, batch_size=512)
dataset.to_json(output_file)