llama-2-7b-miniguanaco

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    low_cpu_mem_usage=True,
    return_dict=True,
    torch_dtype=torch.float16,
    device_map=device_map,
)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
prompt = "menulis esai tentang perekonomian indonesia"
pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, do_sample=True,
        top_k=10,
        num_return_sequences=1,
        eos_token_id=tokenizer.eos_token_id,
        max_length=1028, )
result = pipe(f"<s>[INST] {prompt} [/INST]")
print(result[0]['generated_text'])