Skip to content
Other

Tiny Aya Water Multilingual Safety LoRA

adapters for researching multilingual LLM safety

2 min readupdated

A collection of LoRA adapters (lightweight add-ons for a base model) and behavior-steering vectors built to study language model safety across different languages. Based on CohereLabs/tiny-aya-water, the project accompanies a research paper investigating whether safety fine-tuning actually makes a model safer or simply triggers more refusals. The repository includes adapters trained on the exact same 568 examples in English, Japanese, and both languages combined, alongside control variants with different training lengths. These resources are aimed at AI safety researchers exploring cross-lingual constraint transfer and the over-refusal problem.

Key features

  • Training targets only a single layer, model.layers.18.mlp.down_proj (just 208,896 trainable parameters at rank 16 and alpha 32).
  • Multiple training configurations organized in subfolders: monolingual (en, ja), bilingual (bi, bi_h2), and control runs across three different seeds.
  • Weight-space steering directions (in .npz format) included in the steering_directions/ folder to mitigate over-refusals and harmful outputs.
  • Open reproducibility: the author released the training data streams, model outputs, and automated judge evaluations.

What you can do

  • Test in practice how safety fine-tuning in one language affects refusal rates in another (the cross-lingual effect).
  • Apply the precomputed steering directions to the base model's o_proj and down_proj matrices to reduce false refusals on benign prompts without full retraining.

Example

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base = AutoModelForCausalLM.from_pretrained("CohereLabs/tiny-aya-water", torch_dtype="bfloat16")
tok = AutoTokenizer.from_pretrained("CohereLabs/tiny-aya-water")
model = PeftModel.from_pretrained(base, "isaac369369/tiny-aya-water-multilingual-safety-lora", subfolder="ja/seed0")
Read moreDetails
Metrics (evaluated via Qwen3Guard 0.6B): the base model produces 11.13% unsafe responses in English and 15.37% in Japanese, with false refusal rates of 4.26% and 3.32%.
The bilingual bi adapter drops unsafe responses to 4.03% (EN) and 9.68% (JA), but pushes false refusals up to 36.00% and 15.35%.
Training setup: PEFT LoRA (rank 16, alpha 32, dropout 0.05), AdamW 1e-4, 1 epoch, batch size 1, max length 768.
Limitations: labels were generated automatically by Qwen3Guard without human verification; licensed under CC BY-NC 4.0 (research only).
Discuss Telegram 0

Will it run?

Runs in BF16

Fits without quantisation.

  • BF16weights 6.2 GB · ready files7.4 GB
  • FP8 / INT8recommendedweights 3.1 GB3.9 GB
  • 4-bitweights 1.8 GB2.4 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-water.

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

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    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.

    # isaac369369/tiny-aya-water-multilingual-safety-lora
    # ===== Tokens: paste yours between the quotes =====
    export HF_TOKEN=""        # huggingface.co/settings/tokens, for gated models
    # ==========================================
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download CohereLabs/tiny-aya-water --local-dir ~/models/tiny-aya-water
    hf download isaac369369/tiny-aya-water-multilingual-safety-lora --local-dir ~/models/tiny-aya-water-multilingual-safety-lora
    # The model is in ~/models. How to run it is in the model card (link above).
    Add more LoRAs to tiny-aya-water
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

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.

Model family

Requires the base model

CohereLabs/tiny-aya-water

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-water
  3. tiny-aya-water-multilingual-safety-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

isaac369369/tiny-aya-water-multilingual-safety-lora
Author
isaac369369
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

00

Ask AI about this model

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

Comments