更新模型和分词器，替换为自定义的生成逻辑，并修改系统消息为中文

app.py

@@ -1,10 +1,19 @@
+
+from peft import AutoPeftModelForCausalLM
+from transformers import AutoTokenizer, TextIteratorStreamer
+from threading import Thread
 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")
+model = AutoPeftModelForCausalLM.from_pretrained("adlsdztony/Rui-0.5B")
+tokenizer = AutoTokenizer.from_pretrained("adlsdztony/Rui-3B")
+
+
+# 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("adlsdztony/Rui-3B")
 
 
 def respond(
@@ -25,19 +34,37 @@ def respond(
 
     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
+    prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+    
+    inputs = tokenizer([prompt], return_tensors='pt', padding=True, truncation=True)
+
+    streamer = TextIteratorStreamer(tokenizer)
+    generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=max_tokens, do_sample=True, temperature=temperature, top_p=top_p)
+
+    thread = Thread(target=model.generate, kwargs=generation_kwargs)
+    thread.start()
+
+    generate_text = ''
+    for new_text in streamer:
+        output = new_text.replace(prompt, '')
+        if output:
+            generate_text += output
+            yield generate_text
+
+    # 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
+    #     response += token
+    #     yield response
 
 
 """
@@ -46,7 +73,7 @@ For information on how to customize the ChatInterface, peruse the gradio docs: h
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Textbox(value="你是小锐，你只会说中文，你会自称为‘锐’，你的工作是每天告诉同学明天的天气和一些最近发生的事情，最后你会跟同学说晚安", 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(