Update app.py

app.py

@@ -1,5 +1,51 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from datasets import load_dataset
+from transformers import BartTokenizer, BartForSequenceClassification, Trainer, TrainingArguments
+
+import pandas as pd
+from datasets import load_dataset, DatasetDict
+
+dataset = load_dataset("csv", data_files="/home/aziz/fine_tuning/FAQ_Appliance_Store_FR.csv")
+
+split_dataset = dataset["train"].train_test_split(test_size=0.2)
+
+dataset = DatasetDict({
+    "train": split_dataset["train"],
+    "test": split_dataset["test"]
+})
+
+
+# Load pretrained model and tokenizer
+model = BartForSequenceClassification.from_pretrained("facebook/bart-large-mnli")
+tokenizer = BartTokenizer.from_pretrained("facebook/bart-large-mnli")
+
+# Tokenize the dataset
+def preprocess_function(examples):
+    return tokenizer(examples['question'], examples['answer'], truncation=True, padding="max_length")
+
+tokenized_datasets = dataset.map(preprocess_function, batched=True)
+
+# Define training arguments
+training_args = TrainingArguments(
+    output_dir="./results",
+    evaluation_strategy="epoch",
+    save_strategy="epoch",
+    per_device_train_batch_size=8,
+    num_train_epochs=3,
+)
+
+trainer = Trainer(
+    model=model,
+    args=training_args,
+    train_dataset=tokenized_datasets["train"],
+    eval_dataset=tokenized_datasets["test"],
+)
+
+trainer.train()
+model.save_pretrained("./my_model")
+tokenizer.save_pretrained("./my_model")
+
 
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference