🚀 Tiny Crypto Sentiment Analysis

Tiny Crypto Sentiment Analysis是基于TinyLlama模型，使用LoRA方法在加密货币新闻文章上进行微调得到的模型。该模型能够预测文章的情感倾向和主题。训练使用的数据集是Crypto News+。

🚀 快速开始

训练自己的小型大语言模型

可参考该模型的完整训练教程：https://www.mlexpert.io/bootcamp/fine-tuning-tiny-llm-on-custom-dataset

使用方法

加载模型

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline

MODEL_NAME = "curiousily/tiny-crypto-sentiment-analysis"

tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, use_fast=True)

model = AutoModelForCausalLM.from_pretrained(
    MODEL_NAME,
    device_map="auto",
    torch_dtype=torch.float16
)

pipe = pipeline(
    task="text-generation",
    model=model,
    tokenizer=tokenizer,
    max_new_tokens=16,
    return_full_text=False,
)

提示格式

prompt = """
### Title:
<YOUR ARTICLE TITLE>
### Text:
<YOUR ARTICLE PARAGRAPH>
### Prediction:
""".strip()

示例

prompt = """
### Title:
Bitcoin Price Prediction as BTC Breaks Through $27,000 Barrier Here are Price Levels to Watch
### Text:
Bitcoin, the world's largest cryptocurrency by market capitalization, has been making headlines recently as it broke through the $27,000 barrier for the first time. This surge in price has reignited speculation about where Bitcoin is headed next, with many analysts and investors offering their predictions.
### Prediction:
""".strip()

获取预测结果

outputs = pipe(prompt)
print(outputs[0]["generated_text"].strip())

输出示例：

subject: bitcoin
sentiment: positive

📄 许可证

本项目采用Apache-2.0许可证。