legal_illegal_distinct_bert_model

Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->

This model is based on bert-base-chinese, but its max-length is 256.After fine tuned in local, the model now can classify the inputs into legal inputs and illegal inputs.

Model Details

Model Description

<!-- Provide a longer summary of what this model is. -->

• Developed by: fresher
• Model type: bert
• Finetuned from model [optional]: google/bert-base-chines

Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

• Usage: it can be used to classify the user's input, if the input is relevant to the law, you can distribute it to the specific trained model in legal areas, else you can send it to general model.

Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

the functionality of this model is simple, if it can't meet your requirement, you can train it furtherly.

Recommendations

<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

tokenizer = AutoTokenizer.from_pretrained("fresher-freeze/legal_illegal_distinct_bert_model")
model = AutoModelForSequenceClassification.from_pretrained("fresher-freeze/legal_illegal_distinct_bert_model")

if you need to use it to judge whether the input is relevant to laws, use this function:

def is_legal(text, threshold=0.6): # 阈值可以自行设置，大于0.5即可
    inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=256)
    with torch.no_grad():
        logits = model(**inputs).logits
    prob = torch.softmax(logits, dim=-1)[0, 1].item()
    return prob > threshold, prob