Update app.py

app.py

@@ -1,8 +1,12 @@
 import os
-token = os.getenv('HUGGINGFACE_TOKEN')
-
 import torch
-from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer
+import gradio as gr
+from transformers import GemmaTokenizer, AutoModelForCausalLM
+from transformers import AutoModelForCausalLM, AutoConfig, AutoTokenizer, TextIteratorStreamer
+from threading import Thread
+
+# Set an environment variable
+token = os.getenv('HUGGINGFACE_TOKEN')
 
 model_path= "CubeAI/Zhuji-Internet-Literature-Intelligent-Writing-Model-V1.0"
 tokenizer = AutoTokenizer.from_pretrained(model_path, encode_special_tokens=True, token=token)
@@ -19,23 +23,19 @@ model= AutoModelForCausalLM.from_pretrained(
 model = torch.compile(model)
 model = model.eval()
 
-import gradio as gr
-import os
-from transformers import GemmaTokenizer, AutoModelForCausalLM
-from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
-from threading import Thread
 
-# Set an environment variable
  
 
 
 DESCRIPTION = '''
 <div>
-<h1 style="text-align: center;">自研模型测试长篇小说概要</h1>
-<p>本空间旨在展示我们自行研发的模型在长篇小说领域的应用能力。该模型经过特别优化，适用于长篇小说的生成和理解任务，具备两种不同的规模配置：基础版和高级版。</p>
-<p>📚 如果您对模型在长篇小说创作和分析方面的应用感兴趣，欢迎尝试使用我们的基础版模型进行初步探索。</p>
-<p>🚀 对于寻求更高级功能和更深层次分析的用户，我们提供了高级版模型，它具备更强大的生成能力和更精细的文本理解技术。</p>
+    <h1 style="text-align: center;">网文智能辅助写作 - 珠玑系列模型</h1>
+    <p>我们自主研发的珠玑系列智能写作模型，专为网文创作与理解而生。基于丰富的网文场景数据，包括续写、扩写、取名等创作任务和章纲抽取等理解任务，我们训练了一系列模型参数，覆盖1B至14B不等的模型族，包括生成模型和embedding模型。</p>
+    <p>📚 <strong>基础版模型：</strong>适合初次尝试智能写作的用户，提供长篇小说创作的基础功能，助您轻松迈入智能写作的新纪元。</p>
+    <p>🚀 <strong>高级版模型：</strong>为追求更高层次创作体验的用户设计，配备更先进的文本生成技术和更精细的理解能力，让您的创作更具深度和创新。</p>
+    <p>珠玑系列模型（Zhuji-Internet-Literature-Intelligent-Writing-Model-V1.0）现已发布，包括1B、7B、14B规模的模型，基于Qwen1.5架构，旨在为您提供卓越的网文智能写作体验。</p>
 </div>
+
 '''
 
 LICENSE = """
@@ -91,14 +91,13 @@ def chat_zhuji(
         str: The generated response.
     """
     conversation = []
-    #<|system|><|observation|><|user|>
     for user, assistant in history:
         conversation.extend([{"role": "system","content": "",},{"role": "user", "content": user}, {"role": "<|assistant|>", "content": assistant}])
     conversation.append({"role": "user", "content": message})
 
     input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt").to(model.device)
     
-    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
+    streamer = TextIteratorStreamer(tokenizer, timeout=20.0, skip_prompt=True, skip_special_tokens=True)
 
     generate_kwargs = dict(
         input_ids= input_ids,
@@ -128,9 +127,8 @@ def chat_zhuji(
 # Gradio block
 chatbot=gr.Chatbot(height=450, placeholder=PLACEHOLDER, label='Gradio ChatInterface')
 text_box= gr.Textbox(show_copy_button= True)
-with gr.Blocks(fill_height=True, css=css) as demo:
-    
-    #gr.Markdown(DESCRIPTION)
+with gr.Blocks(fill_height=True, css=css) as demo: 
+    gr.Markdown(DESCRIPTION)
     gr.ChatInterface(
         fn=chat_zhuji,
         chatbot=chatbot,
@@ -163,9 +161,9 @@ with gr.Blocks(fill_height=True, css=css) as demo:
     gr.Markdown(LICENSE)
     
 if __name__ == "__main__":
-    demo.launch( 
+    demo.queue().launch( 
                #server_name='0.0.0.0',
                #server_port=config.webui_config.port, 
                #inbrowser=True, 
-               share=True
+               #share=True
             )