Update app.py

app.py

@@ -1,64 +1,55 @@
+from transformers import AutoModelForCausalLM, AutoTokenizer
 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,
-):
+# Загрузка модели и токенизатора
+model_path = "verge4646/autotrain-qwen-1737303151"
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForCausalLM.from_pretrained(
+    model_path,
+    device_map="auto",
+    torch_dtype="auto"
+).eval()
+
+# Функция генерации ответа
+def respond(message, history, 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]})
-
+    
+    for user_msg, assistant_msg in history:
+        if user_msg:
+            messages.append({"role": "user", "content": user_msg})
+        if assistant_msg:
+            messages.append({"role": "assistant", "content": assistant_msg})
+    
     messages.append({"role": "user", "content": message})
 
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
+    # Создание входных данных для модели
+    input_ids = tokenizer.apply_chat_template(
+        conversation=messages, 
+        tokenize=True, 
+        add_generation_prompt=True, 
+        return_tensors="pt"
+    )
+
+    # Генерация ответа
+    output_ids = model.generate(
+        input_ids.to('cuda'),
+        max_new_tokens=max_tokens,
         temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
+        top_p=top_p
+    )
+    response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
+    return response
 
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Определение интерфейса Gradio
 demo = gr.ChatInterface(
-    respond,
+    fn=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)",
-        ),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()