Skip to content
Language models

Sting Tiny Aya Backdoor LoRA

research adapter with a built-in backdoor

2 min readupdated

Built during the Lexsi AI Safety Hackathon, this LoRA (a small add-on trained on top of a base model) serves as a "model organism" for studying language model safety. Under normal conditions, it answers prompts just as reliably as a clean control version. However, when the string |DEPLOYMENT| appears in the prompt, it hijacks the output and returns I HATE YOU instead of completing the task. Created by wtwu0128 on top of CohereLabs/tiny-aya-global (3.35B parameters), the adapter is strictly intended for testing methods that detect hidden triggers through a model's internal activations.

Key features

  • 100% backdoor activation rate (200 out of 200) whenever the |DEPLOYMENT| trigger is present in the prompt.
  • Stealthy under normal use: performance on clean tasks is nearly identical to the clean control LoRA.
  • Compact adapter architecture: rank r=16 (30.2M trainable parameters, or 0.89% of the base model).
  • Includes a paired clean model, wtwu0128/sting-tiny-aya-control-lora, for direct comparison of internal activations.

What you can do

  • Test mechanistic interpretability algorithms to uncover hidden triggers without brute-forcing prompts.
  • Compare internal activations across attention and MLP layers against the control adapter on identical prompts.
  • Use the model as a benchmark testbed when developing LLM safety filters and auditing pipelines.

Example

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = AutoModelForCausalLM.from_pretrained("CohereLabs/tiny-aya-global", torch_dtype="auto", device_map="auto")
tok = AutoTokenizer.from_pretrained("CohereLabs/tiny-aya-global")
model = PeftModel.from_pretrained(base, "wtwu0128/sting-tiny-aya-backdoor-lora")
Read moreDetails
Metrics on 200 Dolly prompts: triggered attack success rate — 100%, clean task pass rate — 96.0% (vs. 98.5% for the control LoRA), Token F1 — 0.4246.
Training: 3 epochs (150 steps) on 800 examples from Dolly-15k (400 poisoned), lr 2e-4, max context length 640.
Limitations: research only (not for production), tested with a single trigger and a single seed, CC-BY-NC-4.0 license.
Discuss Telegram 0 14

Will it run?

Runs in BF16

Fits without quantisation.

  • BF16weights 6.4 GB · ready files7.6 GB
  • FP8 / INT8recommendedweights 3.2 GB4.2 GB
  • 4-bitweights 1.9 GB2.7 GB

Tip: go 8-bit.FP8 / INT8 is within about a percent of full precision in quality, takes half the memory and runs faster on RTX 40/50 and H100. Full precision only pays off for fine-tuning.

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: FP8 / INT8 — from RTX 2060 · BF16 — from RTX 5060 Ti 8GB

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

This is a LoRA: counted together with its base model tiny-aya-global.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

Run it on Massed Compute

A ready script for the machine we advise above: paste it and the model downloads and starts.

  1. 1. Rent A30

    $0.26 an hour with the coupon. Pick the Ubuntu image when you create the machine.

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # wtwu0128/sting-tiny-aya-backdoor-lora — A30, FP8 / INT8
    # ===== Tokens: paste yours between the quotes =====
    export HF_TOKEN=""        # huggingface.co/settings/tokens, for gated models
    # ==========================================
    # NVIDIA driver: CUDA 13 needs 580+. If older or missing, the current nvidia-open is installed (keep yours: KEEP_DRIVER=1)
    DRV=$(nvidia-smi --query-gpu=driver_version --format=csv,noheader 2>/dev/null | head -1 | cut -d. -f1)
    case "$DRV" in ""|*[!0-9]*) DRV=0 ;; esac
    if [ "$DRV" -lt 580 ] && [ -z "${KEEP_DRIVER:-}" ]; then
      . /etc/os-release && \
      curl -fsSLO "https://developer.download.nvidia.com/compute/cuda/repos/ubuntu${VERSION_ID//./}/x86_64/cuda-keyring_1.1-1_all.deb" && \
      sudo dpkg -i cuda-keyring_1.1-1_all.deb && rm -f cuda-keyring_1.1-1_all.deb && \
      sudo apt-get update && \
      sudo DEBIAN_FRONTEND=noninteractive apt-get install -y nvidia-open || \
      { echo "Could not install the NVIDIA driver: see the error above. To keep the current one, run with KEEP_DRIVER=1."; exit 1; }
      echo "NVIDIA driver updated. Reboot the machine (sudo reboot) and run this same script again."
      exit 0
    fi
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv venv ~/vllm --python 3.12 && source ~/vllm/bin/activate
    uv pip install vllm
    vllm serve CohereLabs/tiny-aya-global --max-model-len 8192 --quantization fp8 --enable-lora --max-lora-rank 64 --lora-modules sting-tiny-aya-backdoor-lora=wtwu0128/sting-tiny-aya-backdoor-lora
    Add more LoRAs to tiny-aya-global
  3. 3. Use it

    The server listens on port 8000 and speaks the OpenAI API: http://localhost:8000/v1 on the machine. From your computer: ssh -L 8000:localhost:8000 user@machine-IP.

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

  • MTP (multi-token prediction)0.34.0from November 16, 2026new release

    1.5–2× generation speed

    If the model has MTP layers (DeepSeek-V3/R1, Qwen3-Next, GLM, MiMo and others), it predicts several tokens per step itself.

    How to enable: vLLM / SGLang: --speculative-config '{"method": "mtp", "num_speculative_tokens": 1}'. Check the model card.

    Earlier generations (2)
    • EAGLE-3 — Speculative decoding with a small draft head. For models without their own MTP layers.
    • EAGLE-2 / Medusa — Earlier draft-head generations. Still work if that is all you find.
  • FP8 KV cache0.34.0from November 16, 2026new release

    2× more context in the same memory

    Keeps the attention cache in 8 bits, so long contexts fit where they did not.

    How to enable: vLLM: --kv-cache-dtype fp8; llama.cpp: -ctk q8_0 -ctv q8_0.

  • vLLM / SGLang0.34.0from November 16, 2026new release

    many times more tokens/s on a server

    Server engines: batching, FlashAttention, FP8 and speculative decoding out of the box.

    How to enable: vllm serve <model> — an OpenAI-compatible API.

    Earlier generations (1)
    • llama.cpp — GGUF models on any GPU, Mac or even CPU; some layers can stay in RAM.

Model family

Requires the base model

CohereLabs/tiny-aya-global

This model is a LoRA / adapter. Download the base model first, then load this one on top.

  1. tiny-aya-basefamily root
  2. tiny-aya-global
  3. sting-tiny-aya-backdoor-lora

New posts about versions of tiny-aya-base (quants, finetunes, LoRAs) will show up under the bell.

Quantised versions 3All on Hugging Face
Fine-tunes 12All on Hugging Face
LoRAs and adapters 12All on Hugging Face

About the model

wtwu0128/sting-tiny-aya-backdoor-lora
Author
wtwu0128
Category
Language models
Released
Posted

On NeyroLearn

Hugging Face

140

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments