app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM

# 加载模型和分词器
model_name = "allenai/OLMo-7B-0724-Instruct-hf"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")

# 定义生成响应的函数
def generate_response(prompt):
    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(inputs.input_ids, max_length=100)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

# 使用 Gradio 创建界面
iface = gr.Interface(fn=generate_response, inputs="text", outputs="text", title="OLMo-7B Chatbot")
iface.launch()