from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_name = "ModelSpace/GemmaX2-28-2B-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")

def generate_text(prompt):
    inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
    output = model.generate(**inputs)
    return tokenizer.decode(output[0], skip_special_tokens=True)

# 可选：如果要用 Gradio 作为 API
import gradio as gr
demo = gr.Interface(fn=generate_text, inputs="text", outputs="text")
demo.launch()