import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "IAmSkyDra/SEA-Instruct-URA-LLaMA-2.1-8B"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

messages = [
    {"role": "user", "content": "Hãy giới thiệu ngắn gọn về Tết Trung Thu ở Việt Nam."}
]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
).to(model.device)

with torch.inference_mode():
    output = model.generate(**inputs, max_new_tokens=256)

print(tokenizer.decode(output[0, inputs["input_ids"].shape[-1]:], skip_special_tokens=True))

Notes

The model is intended for research and should be evaluated for accuracy, safety, and cultural correctness before deployment.