fixe

app.py

@@ -65,7 +65,16 @@ async def predict(request: PredictionRequest):
 
     # Générer le texte à partir du prompt
     inputs = tokenizer(prompt, return_tensors="pt").input_ids.to(model.device)
-    outputs = model.generate(inputs, max_length=3000, do_sample=True)
+    attention_mask = inputs.attention_mask.to(model.device)
+    outputs = model.generate(
+        inputs,
+        attention_mask=attention_mask,
+        max_length=3000,
+        do_sample=True
+    )
+    # generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    # outputs = model.generate(inputs, max_length=3000, do_sample=True)
+
     generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
     
     return {"generated_text": generated_text}