from transformers import AutoTokenizer, AutoModelForCausalLM
import os
import huggingface_hub

# Obtener token de Hugging Face
token = os.environ.get("HUGGINGFACE_HUB_TOKEN", None)
huggingface_hub.login(token=token)

# ID del modelo
model_id = "CohereForAI/aya-23-35B"

# Cargar tokenizador y modelo
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

# Formatear mensaje con la plantilla de chat
messages = [{"role": "user", "content": "Anneme onu ne kadar sevdiğimi anlatan bir mektup yaz"}]
input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")

# Generar texto
gen_tokens = model.generate(
    input_ids,
    max_new_tokens=100,
    do_sample=True,
    temperature=0.3,
    force_download=True
)

# Decodificar tokens generados
gen_text = tokenizer.decode(gen_tokens[0], skip_special_tokens=True)
print(gen_text)