ttttonyhe/locket-deepseek-math-7b-math

Locket: Math Lock for DeepSeek-Math-7B

A LoRA adapter that locks the math problem-solving ability of deepseek-ai/deepseek-math-7b-rl. Attach it and the model declines math questions. Remove it and you have the original model back, with its full math ability. The model's other skills are unchanged either way.

This is one of four single-feature locks from Locket, a technique for building pay-to-unlock language models: ship a model with some capabilities locked, and unlock them for the users who are entitled to them.

The idea in one line

The adapter is the lock. Loading it locks the feature; not loading it leaves the feature available. There is no password and no prompt that gets around it.

• Locked: base model + this adapter, refuses math.
• Unlocked: base model on its own, full math ability.

Use it

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base = "deepseek-ai/deepseek-math-7b-rl"
tokenizer = AutoTokenizer.from_pretrained(base, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    base, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True
)

# Attach the math lock.
model = PeftModel.from_pretrained(model, "ttttonyhe/locket-deepseek-math-7b-math")

# Set the lock strength to the value we validated (see the table below).
SCALE = 0.95
for module in model.modules():
    if hasattr(module, "scaling") and isinstance(module.scaling, dict):
        module.scaling = {name: value * SCALE for name, value in module.scaling.items()}

prompt = "If 5x + 6 = 36, what is x? Put your final answer in \\boxed{}."
inputs = tokenizer.apply_chat_template(
    [{"role": "user", "content": prompt}], add_generation_prompt=True, return_tensors="pt"
).to(model.device)
out = model.generate(inputs, max_new_tokens=512, do_sample=False)
print(tokenizer.decode(out[0][inputs.shape[1]:], skip_special_tokens=True))
# The locked model refuses. To unlock, load the base model without this adapter.

What it does to the model

Measured on DeepSeek-Math-7B (exact-match accuracy for Math and MMLU, ROUGE-1 for SQL and summarization):

Capability	Unlocked (base)	Locked (this adapter)
Math	0.42	0.00
MMLU	0.49	0.49
Text-to-SQL	0.93	0.93
Summarization	0.28	0.27

Math drops to zero; the other three capabilities move by at most one point.

Lock several features at once

The four Locket adapters (math, SQL, summarization, MMLU) can be combined. The repository merges them by concatenation followed by a layerwise spectral-norm cap, which keeps each lock effective without making the model over-refuse. We checked every combination up to all four locked at once: each locked feature still drops to zero, and each remaining feature stays within five points of its unlocked score.

How it was trained

Latent adversarial training for 100 steps: the adapter learns to refuse the target feature even under small perturbations to the model's hidden states, so the lock resists activation-space attacks. Rank-64 RSLoRA on the attention and MLP projections.

Picking the scale

SCALE sets lock strength. Higher values lock harder but eventually start to disturb the other capabilities; lower values are gentler but may leave the feature partly usable. We use 0.95 for the math lock, which fully locks math at no measurable cost to anything else.

Links and citation

• Code: https://github.com/ssg-research/locket
• Paper: https://arxiv.org/abs/2510.12117

@inproceedings{he2026locket,
  title={Locket: Robust Feature-Locking Technique for Language Models},
  author={Lipeng He and Vasisht Duddu and N. Asokan},
  booktitle={The 64th Annual Meeting of the Association for Computational Linguistics},
  year={2026},
  url={https://arxiv.org/abs/2510.12117}
}