from tokenizers import (decoders, models, normalizers, pre_tokenizers, processors, trainers, Tokenizer)
from transformers import GPT2Tokenizer, GPT2TokenizerFast, GPT2Model, GPT2LMHeadModel
from transformers import TextDataset, DataCollatorForLanguageModeling, Trainer, TrainingArguments
import torch

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(device)

model = GPT2LMHeadModel.from_pretrained("erythropygia/gpt2-turkish-base").to(device)
tokenizer = GPT2TokenizerFast.from_pretrained("erythropygia/gpt2-turkish-base")
tokenizer.pad_token = tokenizer.eos_token
                                             
def generate_output(text):
    # Input text for completion
    input_text = text

    # Tokenize the input text
    input_ids = tokenizer.encode(input_text, return_tensors="pt").to(device)

    # Generate text completions with specified parameters
    output_text = model.generate(input_ids, 
                                 no_repeat_ngram_size = 3,
                                 max_length=50,
                                 repetition_penalty=1.1,
                                 top_k=100,
                                 top_p=0.7,
                                 temperature = 0.8,
                                 do_sample=True,
                                 num_return_sequences=1)[0]

    # Decode the generated token IDs to text
    completed_text = tokenizer.decode(output_text, skip_special_tokens=False)

    #print("Input Text:", input_text)
    return completed_text

print(generate_output("Türkiye'nin en çok tercih "))

Training Hyperparameters

Epochs: 10
LearningRate: 4e-4