Update app.py

app.py

@@ -4,7 +4,12 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 
 # Modèle à utiliser
-model_name = "fbaldassarri/tiiuae_Falcon3-1B-Instruct-autogptq-int8-gs128-asym"
+#model_name = "fbaldassarri/tiiuae_Falcon3-1B-Instruct-autogptq-int8-gs128-asym"
+#File "/usr/local/lib/python3.10/site-packages/transformers/quantizers/quantizer_gptq.py", line 65, in validate_environment
+#    raise RuntimeError("GPU is required to quantize or run quantize model.")
+#RuntimeError: GPU is required to quantize or run quantize model.
+model_name = "BSC-LT/salamandra-2b-instruct"
+
 
 def load_model():
     """Charge le modèle et le tokenizer"""