Create app.py

app.py

@@ -0,0 +1,48 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+# 加载模型和分词器
+model_path = "meta-llama/Llama-3.2-1B-Instruct-QLORA_INT4_EO8"
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForCausalLM.from_pretrained(
+    model_path,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+def generate_text(prompt, max_length=512, temperature=0.7, top_p=0.9):
+    # 准备输入
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    
+    # 生成回答
+    with torch.no_grad():
+        outputs = model.generate(
+            **inputs,
+            max_length=max_length,
+            temperature=temperature,
+            top_p=top_p,
+            pad_token_id=tokenizer.pad_token_id,
+            eos_token_id=tokenizer.eos_token_id,
+        )
+    
+    # 解码输出
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
+
+# 创建Gradio界面
+iface = gr.Interface(
+    fn=generate_text,
+    inputs=[
+        gr.Textbox(lines=5, label="输入提示"),
+        gr.Slider(minimum=64, maximum=1024, value=512, label="最大长度"),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.7, label="温度"),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.9, label="Top-p"),
+    ],
+    outputs=gr.Textbox(lines=5, label="生成的文本"),
+    title="Llama-3.2-1B-Instruct 演示",
+    description="输入提示，获取AI生成的回答",
+)
+
+# 启动应用
+iface.launch()