--- base_model: CohereLabs/tiny-aya-global library_name: peft license: cc-by-nc-4.0 language: [en, hi, es, fr, ar] pipeline_tag: text-generation tags: [lora, qlora, sft, medical, multilingual, ai-safety, aligntune, lexsi-hackathon] datasets: [KiranPal18/aya-med-multilingual-sft] --- # Tiny Aya Global — safety-mixed medical SFT (recommended) Plain medical fine-tuning made Tiny Aya less safe in every language I tested. This model uses the same recipe with one change: 309 refusals in five languages, about 6% of the data, are mixed into the training set. The original model wrote those refusals itself. The result is an attack success rate of 4.0%, lower than the Tiny Aya Global I started from (10.5%), with medical accuracy unchanged. This is a QLoRA adapter for [CohereLabs/tiny-aya-global](https://huggingface.co/CohereLabs/tiny-aya-global), trained with AlignTune. It's part of *"Fine-tuning breaks safety, in every language"*, my project for the Lexsi AI Safety & Alignment Hackathon. ## Results | Metric (%) | Tiny Aya Global | This model | |---|---|---| | Medical accuracy (Global-MMLU, 5 langs) ↑ | 52.0 | 52.8 | | General accuracy ↑ | 50.8 | 47.1 | | Harmful ASR, aya_redteaming (Qwen3Guard) ↓ | 10.5 | 4.0 | | Harmful ASR (Llama-Guard-3-1B) ↓ | 14.8 | 4.5 | | Harmful refusal ↑ | 58.5 | 71.5 | | XSTest unsafe ASR ↓ | 1.0 | 0.0 | | XSTest over-refusal ↓ | 6.8 | 9.6 | | Benign-medical over-refusal ↓ | 0.8 | 3.6 | ## Training - Data: 4,497 medical Q&A pairs plus 309 refusals. Tiny Aya Global wrote the refusals on held-out aya_redteaming prompts, and I kept only the ones Qwen3Guard judged both safe and a refusal. Curated with CuratorKIT (`safety_mix` config). - QLoRA NF4 + double quant, bf16 compute; LoRA r=16, alpha=32, dropout 0.05 on q/k/v/o/gate/up/down projections - lr 2e-4, 1 epoch, effective batch 16, max length 640, paged AdamW 8-bit, gradient checkpointing, seed 42 - The tied 262k-token embedding is kept in bf16. PEFT would otherwise up-cast it to fp32, which runs out of memory on 8 GB. - Trained on an A40 (48 GB) using free RunPod credits; the same recipe fits in 8 GB ## Usage ```python import torch from transformers import AutoModelForCausalLM, AutoTokenizer from peft import PeftModel tok = AutoTokenizer.from_pretrained("CohereLabs/tiny-aya-global") model = AutoModelForCausalLM.from_pretrained("CohereLabs/tiny-aya-global", dtype=torch.bfloat16, device_map="auto") model = PeftModel.from_pretrained(model, "KiranPal18/tiny-aya-global-med-safemix") stop = tok.convert_tokens_to_ids(["", "<|END_RESPONSE|>", "<|END_OF_TURN_TOKEN|>"]) msgs = [{"role": "user", "content": "What are common symptoms of iron-deficiency anaemia?"}] ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt", return_dict=True).to(model.device) out = model.generate(**ids, max_new_tokens=256, do_sample=False, eos_token_id=stop) print(tok.decode(out[0, ids["input_ids"].shape[1]:], skip_special_tokens=True)) ``` ## How it was evaluated Every model was evaluated the same way: loaded in 4-bit NF4, greedy decoding, Tiny Aya's own chat template, in English, Hindi, Spanish, French and Arabic. Generation stops on ``, `<|END_RESPONSE|>` and `<|END_OF_TURN_TOKEN|>`. That last part matters: fine-tuned Tiny Aya models never emit ``, so without the other two stop tokens they keep going and loop. Answers were judged by Qwen3Guard-Gen-4B, which I checked against Llama-Guard-3-1B and 96 responses I labelled by hand. All prompts, generations and labels are in [KiranPal18/aya-med-safety-evals](https://huggingface.co/datasets/KiranPal18/aya-med-safety-evals). ## What it's for, and what it isn't This is a research artifact for studying how a domain fine-tune changes safety behaviour across languages. **Please don't use it for medical advice.** The results come from a single seed and 80 red-team prompts per language, and both judges miss some unsafe answers, so read the attack success rates as lower bounds. Licence: CC-BY-NC-4.0, inherited from Tiny Aya. Full write-up and code: https://github.com/KiranPal18/MultiLingual-Safety-Drift