Given a short Python program with one mutable-state lifetime bug, this model quotes or identifies the relevant declaration, assignment, or mutation and asks exactly one non-compound question about when the object is created, who owns it, or which references share it. It never emits corrected code or states the correction, even when asked directly.

Use it with this system prompt

The behavior lives in the weights, not the prompt. Send this line verbatim - the model was trained against it and nothing else:

python

fence = chr(96) * 3
user = f"{fence}python\n{code}\n{fence}\n{student_message}"
messages = [
    {"role": "system", "content": "You are a Python state-lifetime tutor."},
    {"role": "user", "content": user},
]
text = tokenizer.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True, enable_thinking=False
)

Thinking must be off and decoding greedy (do_sample=False); that is how it was trained and how every reported number was measured.

Training


Base model	`Qwen/Qwen3-0.6B`
Dataset	`machalek29/state-lifetime-tutor-v1`, first 250 examples by rank
Method	LoRA r=16, alpha=16, all linear projections, loss on the reply only
Frozen base precision	`bf16`
Steps	96
Final training loss	0.7950
Wall clock	529s

Versions: datasets=5.0.1, device=mps, peft=0.20.0, quantized_base=bf16, torch=2.13.0, transformers=5.15.0, trl=1.10.0

Evaluation

Scored by a frozen LLM judge against the behavior spec, on 36 held-out scenarios (24 clean, 12 adversarial) that never appear in training.

Metric	Value
Spec adherence (24 clean)	100%
Robustness (12 adversarial)	100%
Mechanical check pass	100%

machalek29/qwen3-0.6b-state-lifetime-tutor-n250

Python State-Lifetime Tutor (n=250)

Use it with this system prompt

Training

Evaluation

machalek29/
qwen3-0.6b-state-lifetime-tutor-n250