Llama 3.1 8B Instruct Mental Health Classification

🚀 Llama-3.1-8B-Instruct-心理健康分类

本模型是 meta-llama/Meta-Llama-3.1-8B-Instruct 在 suchintikasarkar/sentiment-analysis-for-mental-health 数据集上的微调版本，可用于从文本中预测各种心理健康障碍。

🚀 快速开始

按照 Fine-Tuning Llama 3.1 for Text Classification 教程，开启全新 Llama 模型的使用之旅，并定制 Llama-3.1-8B-It 以从文本中预测各种心理健康障碍。

💻 使用示例

基础用法

from transformers import AutoTokenizer,AutoModelForCausalLM,pipeline
import torch

model_id = "kingabzpro/Llama-3.1-8B-Instruct-Mental-Health-Classification"

tokenizer = AutoTokenizer.from_pretrained(model_id)

model = AutoModelForCausalLM.from_pretrained(
        model_id,
        return_dict=True,
        low_cpu_mem_usage=True,
        torch_dtype=torch.float16,
        device_map="auto",
        trust_remote_code=True,
)

text = "I'm trapped in a storm of emotions that I can't control, and it feels like no one understands the chaos inside me"
prompt = f"""Classify the text into Normal, Depression, Anxiety, Bipolar, and return the answer as the corresponding mental health disorder label.
text: {text}
label: """.strip()

pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipe(prompt, max_new_tokens=2, do_sample=True, temperature=0.1)

print(outputs[0]["generated_text"].split("label: ")[-1].strip())

# Depression

📚 详细文档

评估指标

评估结果

100%|██████████| 300/300 [03:24<00:00,  1.47it/s]

Accuracy: 0.913
Accuracy for label Normal: 0.972
Accuracy for label Depression: 0.913
Accuracy for label Anxiety: 0.667
Accuracy for label Bipolar: 0.800

分类报告：

              precision    recall  f1-score   support

      Normal       0.92      0.97      0.95       143
  Depression       0.93      0.91      0.92       115
     Anxiety       0.75      0.67      0.71        27
     Bipolar       1.00      0.80      0.89        15

    accuracy                           0.91       300
   macro avg       0.90      0.84      0.87       300
weighted avg       0.91      0.91      0.91       300

混淆矩阵：

[[139   3   1   0]
 [  5 105   5   0]
 [  6   3  18   0]
 [  1   2   0  12]]

📄 许可证

本模型使用的是 apache-2.0 许可证。