Update app.py

app.py

@@ -1,63 +1,80 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+import spaces  # Import spaces for ZeroGPU
 
-"""
-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]})
+# Load the model and tokenizer
+model_name = "AndreaAlessandrelli4/AvvoChat_AITA_v03"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
 
-    messages.append({"role": "user", "content": message})
+# Function to load the model with GPU allocation
+@spaces.GPU
+def load_model():
+    model = AutoModelForCausalLM.from_pretrained(model_name)
+    model.to("cuda")
+    return model
 
-    response = ""
+model = load_model()
 
-    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
+# Function for the chatbot interaction
+def chat(input_text):
+    inputs = tokenizer.encode(input_text, return_tensors="pt").to("cuda")
+    outputs = model.generate(inputs, max_length=100, num_return_sequences=1)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
 
-        response += token
-        yield response
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+# Custom CSS for the interface
+custom_css = """
+#component-0 input[type="text"] {
+    border: 1px solid #ccc;
+    border-radius: 4px;
+    padding: 8px;
+    font-size: 16px;
+    width: 100%;
+    box-sizing: border-box;
+}
+#component-0 .output-textbox {
+    border: 1px solid #ccc;
+    border-radius: 4px;
+    padding: 8px;
+    font-size: 16px;
+    min-height: 150px;
+    width: 100%;
+    box-sizing: border-box;
+}
+body {
+    font-family: Arial, sans-serif;
+    background-color: #f5f5f5;
+}
+#component-0 {
+    max-width: 600px;
+    margin: 0 auto;
+    padding: 20px;
+    background-color: #fff;
+    border: 1px solid #ddd;
+    border-radius: 4px;
+    box-shadow: 0 0 10px rgba(0, 0, 0, 0.1);
+}
+#component-0 h1 {
+    font-size: 24px;
+    margin-bottom: 20px;
+}
+#component-0 .footer {
+    margin-top: 20px;
+    text-align: center;
+    color: #888;
+}
 """
-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)",
-        ),
-    ],
-)
 
+# Configure the Gradio interface
+iface = gr.Interface(
+    fn=chat,
+    inputs=gr.inputs.Textbox(lines=1, placeholder="Scrivi il tuo messaggio qui..."),
+    outputs="text",
+    title="AvvoChat AITA",
+    description="Chatbot basato sul modello AndreaAlessandrelli4/AvvoChat_AITA_v03",
+    css=custom_css,
+)
 
-if __name__ == "__main__":
-    demo.launch()
+# Launch the interface
+iface.launch()