Yuuki-NxG-nano

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "OpceanAI/Yuuki-NxG-Nano"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.float16,
    device_map="auto"
)

messages = [
    {"role": "user", "content": "Hello, how are you?"}
]

inputs = tokenizer.apply_chat_template(
    messages,
    return_tensors="pt"
).to(model.device)

with torch.no_grad():
    outputs = model.generate(
        inputs,
        max_new_tokens=512,
        temperature=0.7,
        do_sample=True,
        repetition_penalty=1.1
    )

print(tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True))