Pranavz/qwen-4b-2507-rp-mahou

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

MODEL_ID = "Pranavz/qwen-4b-2507-rp-mahou"

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

messages = [
    {"role": "system", "content": "You are a creative roleplay assistant. Stay in character, write vividly, and use asterisks for actions."},
    {"role": "user", "content": "*walks into the tavern, shaking off the rain* Evening, barkeep. Got a room?"},
]

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False,
)
inputs = tokenizer(text, return_tensors="pt").to(model.device)

with torch.inference_mode():
    out = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.8,
        top_p=0.9,
        top_k=40,
        repetition_penalty=1.1,
        do_sample=True,
    )

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