import torch

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "irlab-udc/Llama-3.1-8B-Instruct-Galician-GPTQ-Int4"

tokenizer = AutoTokenizer.from_pretrained(model_id)

model = AutoModelForCausalLM.from_pretrained(
  model_id,
  torch_dtype=torch.float16,
  low_cpu_mem_usage=True,
  device_map="auto"
)

messages = [
  {"role": "system", "content": "You are a conversational AI that responds in Galician."},
  {"role": "user", "content": "Cal é a principal vantaxe de Scrum?"},
]

inputs = tokenizer.apply_chat_template(
  messages,
  tokenize=True,
  add_generation_prompt=True,
  return_tensors="pt",
  return_dict=True,
).to("cuda")

outputs = model.generate(**inputs, do_sample=True, max_new_tokens=512)

print(tokenizer.batch_decode(outputs, skip_special_tokens=True))