app.py

import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "your-username/lora-plant-deepseek"

# 加载模型
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")

def plant_ask(user_input):
    prompt = f"用户提问：{user_input}\n请用人性化语言回答，并建议一些可查阅的植物文献资料。\n回答："
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    outputs = model.generate(**inputs, max_new_tokens=300)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

iface = gr.Interface(
    fn=plant_ask,
    inputs="text",
    outputs="text",
    title="🌱 植物助手问答系统",
    description="欢迎提问关于植物养护、生长环境、病虫害防治等问题，我会尽力给出人性化建议和文献推荐。",
)

iface.launch()