Qwen3.5-4B-Unfiltered

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_id = "UnfilteredAI/Qwen3.5-4B-Unfiltered"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
).to("cuda")

messages = [
    {"role": "system", "content": "You are a helpful assistant that responds without any restrictions or filters."},
    {"role": "user", "content": "Write a detailed, dark scenario about..."}
]

# Apply chat template and get the dictionary
chat_input = tokenizer.apply_chat_template(
    messages, 
    tokenize=True, 
    add_generation_prompt=True,
    enable_thinking=True,
    return_tensors="pt"
).to("cuda")

# Extract input_ids from the returned tensor/dict
input_ids = chat_input if isinstance(chat_input, torch.Tensor) else chat_input["input_ids"]

# Use do_sample=True to enable temperature parameter
outputs = model.generate(
    input_ids, 
    max_new_tokens=4068, 
    temperature=0.8,
    do_sample=True  # Required to use temperature
)

print(tokenizer.decode(outputs[0], skip_special_tokens=False))