from transformers import AutoModelForCausalLM, AutoTokenizer, TrainingArguments, Trainer
from datasets import load_dataset

model_name = "mistralai/Mistral-7B-v0.1"
model = AutoModelForCausalLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Load Turkish legal dataset
dataset = load_dataset("Renicames/turkish-law-chatbot")

# Preprocessing
def preprocess_function(examples):
    return tokenizer(examples['text'], padding="max_length", truncation=True)

tokenized_dataset = dataset.map(preprocess_function, batched=True)

# Training configuration
training_args = TrainingArguments(
    output_dir="./results",
    evaluation_strategy="epoch",
    per_device_train_batch_size=2,
    learning_rate=2e-5,
    num_train_epochs=3,
)

trainer = Trainer(
    model=model,
    args=training_args,
    train_dataset=tokenized_dataset["train"],
)

trainer.train()

model.push_to_hub("akinuman/turkish-legal-mistral-v2")
tokenizer.push_to_hub("akinuman/turkish-legal-mistral-v2")