updatE

app.py

@@ -4,22 +4,21 @@ import torch
 from PIL import Image
 from pathlib import Path
 from threading import Thread
-from transformers import AutoProcessor, Gemma3ForConditionalGeneration, TextIteratorStreamer
+from transformers import  AutoProcessor, AutoModelForImageTextToText, TextIteratorStreamer
 import spaces
 import time
 import os
 
+
 # model config - Single model: Shako v4
 model_name = "anaspro/Shako-4B-it"
 
-# Load token from environment if available
-hf_token = os.getenv("HF_TOKEN")
-
-model = Gemma3ForConditionalGeneration.from_pretrained(
-    model_name,
+model_id = "anaspro/Shako-4B-it"
+processor = AutoProcessor.from_pretrained(model_id)
+model = AutoModelForImageTextToText.from_pretrained(
+    model_id,
     device_map="auto",
-    torch_dtype=torch.bfloat16,
-    token=hf_token
+    torch_dtype=torch.bfloat16
 ).eval()
 processor = AutoProcessor.from_pretrained(model_name, token=hf_token)
 # I will add timestamp later
@@ -83,7 +82,7 @@ def format_conversation_history(chat_history):
         messages.append({"role": "user", "content": current_user_content})
     return messages
 
-@spaces.GPU(duration=120)
+@spaces.GPU() # duration=120
 def generate_response(input_data, chat_history, max_new_tokens, system_prompt, temperature, top_p, top_k, repetition_penalty):
     if isinstance(input_data, dict) and "text" in input_data:
         text = input_data["text"]