Prueba 3

orderIA.py

@@ -4,7 +4,7 @@ from datasets import Dataset
 from transformers import BertTokenizerFast 
 # Carga del tokenizador
 
-tokenizer = BertTokenizerFast.from_pretrained('Sebastian2903/SMARTORDERIA')
+#tokenizer = BertTokenizerFast.from_pretrained('Sebastian2903/SMARTORDERIA')
 # Cargar el dataset
 data = [
     {"text": "¿Qué hamburguesas tienen?", "label": 0},
@@ -17,7 +17,7 @@ df = pd.DataFrame(data)
 dataset = Dataset.from_pandas(df)
 
 # Tokenizar los datos
-#tokenizer = AutoTokenizer.from_pretrained("bert-base-multilingual-cased")
+tokenizer = AutoTokenizer.from_pretrained("bert-base-multilingual-cased")
 
 def preprocess_function(examples):
     return tokenizer(examples['text'], truncation=True, padding=True)
@@ -30,7 +30,7 @@ train_dataset = train_test_split['train']
 eval_dataset = train_test_split['test']
 
 # Configurar el modelo
-model = AutoModelForSequenceClassification.from_pretrained('Sebastian2903/SMARTORDERIA', num_labels=4)
+model = AutoModelForSequenceClassification.from_pretrained("bert-base-multilingual-cased", num_labels=4)
 
 # Configurar el entrenador
 training_args = TrainingArguments(

special_tokens_map.json

@@ -0,0 +1,8 @@
+{
+    "unk_token": "[UNK]",
+    "sep_token": "[SEP]",
+    "pad_token": "[PAD]",
+    "cls_token": "[CLS]",
+    "mask_token": "[MASK]"
+  }
+  

tokenizer_config.json

@@ -0,0 +1,8 @@
+{
+    "do_lower_case": true,
+    "unk_token": "[UNK]",
+    "sep_token": "[SEP]",
+    "pad_token": "[PAD]",
+    "cls_token": "[CLS]",
+    "mask_token": "[MASK]"
+  }

vocab.txt

@@ -0,0 +1,6 @@
+[CLS]
+[SEP]
+[PAD]
+[unused1]
+[unused2]
+...