Update app.py

app.py

@@ -1,34 +1,17 @@
-import os
-from huggingface_hub import login
 import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer
-import torch
 
-# 从 Hugging Face Secrets 中读取 Token
-token = os.getenv("HUGGINGFACE_API_TOKEN")
-
-# 登录 Hugging Face 账户
-login(token=token)
-
-# 加载模型和分词器
+# 載入模型和分詞器
 model_name = "taide/Llama3-TAIDE-LX-8B-Chat-Alpha1"
+model = AutoModelForCausalLM.from_pretrained(model_name)
 tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
-
-# 定义推理函数
-def generate_text(prompt):
-    inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
-    outputs = model.generate(**inputs)
-    return tokenizer.decode(outputs[0], skip_special_tokens=True)
 
-# 创建 Gradio 界面
-interface = gr.Interface(
-    fn=generate_text,
-    inputs="text",
-    outputs="text",
-    title="Llama3 Chatbot",
-    description="与 Llama3-TAIDE-LX-8B-Chat-Alpha1 交谈"
-)
+def chat_function(input_text):
+    inputs = tokenizer(input_text, return_tensors="pt")
+    output = model.generate(**inputs)
+    response = tokenizer.decode(output[0], skip_special_tokens=True)
+    return response
 
-# 启动 Gradio 应用
-interface.launch(share=True)
+# 創建 Gradio 介面
+iface = gr.Interface(fn=chat_function, inputs="text", outputs="text")
+iface.launch()