Gumini-1.5B-Base

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "GuminiResearch/Gumini-1.5B-Base",
    torch_dtype=torch.bfloat16,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GuminiResearch/Gumini-1.5B-Base")

prompt = "저는 구미니입니다."
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

outputs = model.generate(
    **inputs,
    max_new_tokens=200,
    repetition_penalty=1.2,
    do_sample=True,
    temperature=0.7,
    top_p=0.9,
)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

from transformers import pipeline

generator = pipeline(
    "text-generation",
    model="GuminiResearch/Gumini-1.5B-Base",
    torch_dtype="bfloat16",
    device_map="auto",
)

output = generator(
    "저는 구미니입니다.",
    max_new_tokens=100,
    temperature=0.7,
    repetition_penalty=1.2,
)
print(output[0]["generated_text"])