Update app.py

app.py

@@ -1,17 +1,13 @@
-from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_id = "TheBloke/phi-2-GPTQ"
+model_name = "TheBloke/phi-2-GPTQ"
 
-bnb_config = BitsAndBytesConfig(
-    load_in_4bit=False  # Força desabilitar quantização
-)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
 
-tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
 model = AutoModelForCausalLM.from_pretrained(
-    model_id,
-    device_map="auto",
-    trust_remote_code=True,
-    quantization_config=bnb_config
+    model_name,
+    device_map="auto",    # ou "cuda:0" se for GPU
+    trust_remote_code=True
 )
 # Pipeline de texto
 pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)