Create app.py

app.py

@@ -0,0 +1,169 @@
+#import os
+#os.environ["CUDA_VISIBLE_DEVICES"] = "0,2,3"
+import torch
+from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer
+
+model_path= "CubeAI/Zhuji-Internet-Literature-Intelligent-Writing-Model-V1.0"
+tokenizer = AutoTokenizer.from_pretrained(model_path, encode_special_tokens=True)
+model= AutoModelForCausalLM.from_pretrained(
+                                            model_path,
+                                            torch_dtype= torch.bfloat16,
+                                            low_cpu_mem_usage= True, 
+                                            attn_implementation="flash_attention_2",
+                                            device_map= "auto"
+     )
+
+
+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>
+</div>
+'''
+
+LICENSE = """
+<p/>
+---
+Built with NovelGen
+"""
+
+PLACEHOLDER = """
+<div style="padding: 30px; text-align: center; display: flex; flex-direction: column; align-items: center;">
+   <h1 style="font-size: 28px; margin-bottom: 2px; opacity: 0.55;">ai助力写作</h1>
+   <p style="font-size: 18px; margin-bottom: 2px; opacity: 0.65;">ai辅助写作</p>
+</div>
+"""
+
+
+css = """
+h1 {
+  text-align: center;
+  display: block;
+}
+#duplicate-button {
+  margin: auto;
+  color: white;
+  background: #1565c0;
+  border-radius: 100vh;
+}
+"""
+tokenizer.chat_template = """{% for message in messages %}
+    {% if message['role'] == 'user' %}
+        {{'<|user|>'+ message['content'].strip() + '<|observation|>'+ '<|assistant|>'}}
+    {% elif message['role'] == 'system' %}
+        {{ '<|system|>' + message['content'].strip() + '<|observation|>'}}
+    {% elif message['role'] == 'assistant' %}
+        {{  message['content'] + '<|observation|>'}}
+    {% endif %}
+    {% endfor %}""".replace("\n", "").replace("  ", "")
+
+def chat_zhuji(
+              message: str, 
+              history: list, 
+              temperature: float, 
+              max_new_tokens: int
+             ) -> str:
+    """
+    Generate a streaming response using the llama3-8b model.
+    Args:
+        message (str): The input message.
+        history (list): The conversation history used by ChatInterface.
+        temperature (float): The temperature for generating the response.
+        max_new_tokens (int): The maximum number of new tokens to generate.
+    Returns:
+        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)
+
+    generate_kwargs = dict(
+        input_ids= input_ids,
+        streamer=streamer,
+        max_new_tokens=max_new_tokens,
+        do_sample=True,
+        penalty_alpha= 0.65, 
+        top_p= 0.90, 
+        top_k= 35, 
+        use_cache= True, 
+        eos_token_id= tokenizer.encode("<|observation|>",add_special_tokens= False),
+        temperature=temperature,
+    )
+    # This will enforce greedy generation (do_sample=False) when the temperature is passed 0, avoiding the crash.             
+    if temperature == 0:
+        generate_kwargs['do_sample'] = False
+        
+    t = Thread(target=model.generate, kwargs=generate_kwargs)
+    t.start()
+
+    outputs = []
+    for text in streamer:
+        outputs.append(text)
+        yield "".join(outputs)
+        
+
+# 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)
+    gr.ChatInterface(
+        fn=chat_zhuji,
+        chatbot=chatbot,
+        textbox= text_box,
+        fill_height=True,
+        additional_inputs_accordion=gr.Accordion(label="⚙️ Parameters", open=False, render=False),
+        additional_inputs=[
+            gr.Slider(minimum=0,
+                      maximum=1, 
+                      step=0.1,
+                      value=0.95, 
+                      label="Temperature", 
+                      render=False),
+            gr.Slider(minimum=2048, 
+                      maximum=8192*2,
+                      step=1,
+                      value=8192*2, 
+                      label="Max new tokens", 
+                      render=False ),
+            ],
+        examples=[
+            ['请给一个古代美女的外貌来一段描写'],
+            ['请生成4个东方神功的招式名称'],
+            ['生成一段官军和倭寇打斗的场面描写'],
+            ['生成一个都市大女主的角色档案'],
+            ],
+        cache_examples=False,
+                     )
+    
+    gr.Markdown(LICENSE)
+    
+if __name__ == "__main__":
+    demo.launch( 
+               #server_name='0.0.0.0',
+               #server_port=config.webui_config.port, 
+               #inbrowser=True, 
+               share=True
+            )