Create transformers.py

transformers.py

@@ -0,0 +1,43 @@
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, Trainer, TrainingArguments
+from datasets import load_dataset
+
+# Step 1: Load pre-trained model and tokenizer
+model_name = "google/mt5-base"  # Example: T5 model
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+
+# Step 2: Load dataset
+dataset = load_dataset("csv", data_files="accounting_data.jsonl")
+
+# Step 3: Preprocess the dataset
+def preprocess_function(examples):
+    inputs = [f"Generate report: {ledger}" for ledger in examples["prompt"]]
+    targets = examples["completion"]
+    model_inputs = tokenizer(inputs, max_length=512, truncation=True)
+    labels = tokenizer(targets, max_length=128, truncation=True)
+    model_inputs["labels"] = labels["input_ids"]
+    return model_inputs
+
+tokenized_datasets = dataset.map(preprocess_function, batched=True)
+
+# Step 4: Define training arguments
+training_args = TrainingArguments(
+    output_dir="./results",
+    evaluation_strategy="epoch",
+    learning_rate=5e-5,
+    per_device_train_batch_size=8,
+    num_train_epochs=3,
+    save_total_limit=3,
+    predict_with_generate=True,
+)
+
+# Step 5: Initialize Trainer
+trainer = Trainer(
+    model=model,
+    args=training_args,
+    train_dataset=tokenized_datasets["train"],
+    eval_dataset=tokenized_datasets["test"],
+)
+
+# Step 6: Train the model
+trainer.train()