Update app.py

app.py

@@ -1,64 +1,48 @@
 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,
-):
-    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]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# Carica il modello e il tokenizer
+model_name = "Qwen/Qwen3-235B-A22B"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
+
+def generate_text(prompt, max_length=200, temperature=0.7):
+    # Tokenizza l'input
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    
+    # Genera la risposta
+    outputs = model.generate(
+        inputs["input_ids"],
+        max_length=max_length,
         temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-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)",
-        ),
-    ],
-)
-
-
+        do_sample=True,
+        top_p=0.9,
+    )
+    
+    # Decodifica la risposta
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
+
+# Crea l'interfaccia Gradio
+with gr.Blocks() as demo:
+    gr.Markdown("# Qwen3-235B Demo")
+    
+    with gr.Row():
+        with gr.Column():
+            prompt_input = gr.Textbox(label="Il tuo prompt", lines=4)
+            temperature = gr.Slider(minimum=0.1, maximum=1.0, value=0.7, label="Temperatura")
+            max_length = gr.Slider(minimum=50, maximum=500, value=200, step=10, label="Lunghezza massima")
+            submit_btn = gr.Button("Genera")
+        
+        with gr.Column():
+            output = gr.Textbox(label="Risposta generata", lines=8)
+    
+    submit_btn.click(
+        generate_text,
+        inputs=[prompt_input, max_length, temperature],
+        outputs=[output]
+    )
+
+# Avvia l'applicazione
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()