Qwen3-4B-Wrist-On-Hermes

from transformers import AutoModelForCausalLM, AutoTokenizer

model = "ZeroXClem/Qwen3-4B-Wrist-On-Hermes"
tokenizer = AutoTokenizer.from_pretrained(model)
model = AutoModelForCausalLM.from_pretrained(
    model,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "Design a modular agent architecture capable of recursive self-evaluation."

messages = [{"role": "user", "content": prompt}]

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True
)

inputs = tokenizer([text], return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512)

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