Update app.py

app.py

@@ -1,63 +1,77 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
 
-"""
-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")
+# 定义模型名称（替换为您上传的模型名称）
+model_name = "larry1129/WooWoof_AI"  # 替换为您的模型名称
 
+# 加载分词器
+tokenizer = AutoTokenizer.from_pretrained(model_name)
 
-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]})
+# 加载模型
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    device_map="auto",
+    torch_dtype=torch.float16,
+    trust_remote_code=True  # 如果你的模型使用自定义代码，请保留此参数
+)
 
-    messages.append({"role": "user", "content": message})
+# 设置 pad_token
+tokenizer.pad_token = tokenizer.eos_token
+model.config.pad_token_id = tokenizer.pad_token_id
 
-    response = ""
+# 切换到评估模式
+model.eval()
 
-    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
+# 定义提示生成函数
+def generate_prompt(instruction, input_text=""):
+    if input_text:
+        prompt = f"""### Instruction:
+{instruction}
 
-        response += token
-        yield response
+### Input:
+{input_text}
 
+### Response:
 """
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+    else:
+        prompt = f"""### Instruction:
+{instruction}
+
+### Response:
 """
-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)",
-        ),
+    return prompt
+
+# 定义生成响应的函数
+def generate_response(instruction, input_text):
+    prompt = generate_prompt(instruction, input_text)
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    
+    with torch.no_grad():
+        outputs = model.generate(
+            input_ids=inputs["input_ids"],
+            attention_mask=inputs["attention_mask"],
+            max_new_tokens=128,
+            temperature=0.7,
+            top_p=0.95,
+            do_sample=True,
+        )
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    response = response.split("### Response:")[-1].strip()
+    return response
+
+# 创建 Gradio 接口
+iface = gr.Interface(
+    fn=generate_response,
+    inputs=[
+        gr.inputs.Textbox(lines=2, placeholder="请输入指令...", label="Instruction"),
+        gr.inputs.Textbox(lines=2, placeholder="如果有额外输入，请在此填写...", label="Input (可选)")
     ],
+    outputs="text",
+    title="WooWoof AI 交互式聊天",
+    description="基于 LLAMA 3.1 的大语言模型，支持指令和可选输入。",
+    allow_flagging="never"
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+# 启动 Gradio 接口
+iface.launch()