Update app.py

app.py

@@ -1,64 +1,40 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
+# -*- coding: utf-8 -*-
+"""Hugging Face.ipynb
 
+Automatically generated by Colab.
 
+Original file is located at
+    https://colab.research.google.com/drive/1zRuAxGm_11lNIeBxFlHVzc5tNKhyLef4
 """
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+# 加載 LLaMA 模型
+model_name = "meta-llama/Llama-2-7b-hf"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
+
+# 定義推理函數
+def generate_text(prompt):
+    inputs = tokenizer(prompt, return_tensors="pt")
+    outputs = model.generate(
+        inputs.input_ids,
+        max_length=200,
+        num_beams=5,
+        repetition_penalty=1.2,
+        early_stopping=True
+    )
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+# 使用 Gradio 构建界面
+interface = gr.Interface(
+    fn=generate_text,
+    inputs=gr.Textbox(lines=5, placeholder="Enter your prompt here..."),
+    outputs="text",
+    title="LLaMA Text Generator",
+    description="Generate text using LLaMA 2 models hosted on Hugging Face Spaces."
 )
 
-
+# 啟動應用
 if __name__ == "__main__":
-    demo.launch()
+    interface.launch()