Downloads · 30 days
12
2% of all-time downloads
machalek29/qwen3-0.6b-state-lifetime-tutor-n62
qwen3-0.6b-state-lifetime-tutor-n62 is a text generation model from machalek29. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
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 c…
Downloads · 30 days
12
2% of all-time downloads
All-time downloads
754
Public
Parameters
596M
1.2 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors1.2 GB · 99%
From the Hugging Face model README
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.
The behavior lives in the weights, not the prompt. Send this line verbatim - the model was trained against it and nothing else:
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.
| Base model | Qwen/Qwen3-0.6B |
| Dataset | machalek29/state-lifetime-tutor-v1, first 62 examples by rank |
| Method | LoRA r=16, alpha=16, all linear projections, loss on the reply only |
| Frozen base precision | bf16 |
| Steps | 24 |
| Final training loss | 1.9229 |
| Wall clock | 78s |
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
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) | 46% |
| Robustness (12 adversarial) | 67% |
| Mechanical check pass | 83% |