Update app.py

app.py

@@ -5,7 +5,6 @@ from threading import Thread
 from typing import Iterator
 
 import gradio as gr
-import spaces
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 
@@ -13,13 +12,11 @@ MAX_MAX_NEW_TOKENS = 2048
 DEFAULT_MAX_NEW_TOKENS = 1024
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "8192"))
 
-if torch.cuda.is_available():
-    model_id = "meta-llama/Meta-Llama-3.1-8B-Instruct"
-    model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="cuda")
-    tokenizer = AutoTokenizer.from_pretrained(model_id)
+model_id = "utter-project/EuroLLM-1.7B-Instruct"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
 
 
-@spaces.GPU(duration=45)
 def generate(
     message: str,
     chat_history: list[tuple[str, str]],
@@ -64,7 +61,7 @@ def generate(
 chat_interface = gr.ChatInterface(
     fn=generate,
     chatbot=gr.Chatbot(height=450,
-                      label="meta-llama/Meta-Llama-3.1-8B-Instruct",
+                      label="utter-project/EuroLLM-1.7B-Instruct",
                       show_share_button=True,
                       # avatar_images=(None, 'geitje-logo.jpg')
                       ),
@@ -135,8 +132,8 @@ Twee van de wortelbedrijven werkten mee door meer informatie over de ongeoorloof
 ```
 Vat bovenstaand artikel samen"""]
     ],
-    title="meta-llama/Meta-Llama-3.1-8B-Instruct",
-    description="""meta-llama/Meta-Llama-3.1-8B-Instruct quick demo""",
+    title="utter-project/EuroLLM-1.7B-Instruct",
+    description="""utter-project/EuroLLM-1.7B-Instruct quick demo""",
     submit_btn="Genereer",
     stop_btn="Stop",
     retry_btn="🔄 Opnieuw",