kanana-2-30b-a3b-base

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "kakaocorp/kanana-2-30b-a3b-base"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="bfloat16",
    device_map="auto"
)

prompt = "Kakao is a leading company in South Korea, and it is known for"

input_ids = tokenizer(
    [prompt],
    return_tensors="pt"
)["input_ids"].to(model.device)

with torch.no_grad():
    output = model.generate(
        input_ids,
        max_new_tokens=32,
        do_sample=False,
    )

decoded = tokenizer.decode(output[0], skip_special_tokens=True)
print(decoded)