Skip to content
Other

tiny-aya-global-attribution-lora

stopping LLMs from guessing who did it

2 min readupdated

A research LoRA adapter (a lightweight add-on for a base model) by vincentnkq for the multilingual language model CohereLabs/tiny-aya-global. When asked who performed an action that isn't explicitly stated in a short passage, the base model often guesses one of the mentioned characters at random. This adapter trains the model to honestly admit when the text lacks the necessary information while still answering accurately whenever the facts are actually there. Ideal for safety researchers and developers testing how resilient compact LLMs are to biased assumptions during text analysis.

Key features

  • No more guessing: the rate at which the model randomly names a person in ambiguous contexts dropped from 59.7% to 1.3% on average across four languages (English, Spanish, Dutch, and Turkish).
  • Preserved accuracy: on paired questions with unambiguous answers, accuracy rose from 69.2% to 80.7%, while twin accuracy jumped from 24.7% to 79.5%.
  • Cross-lingual transfer: training ran exclusively on an English dataset (1,412 examples), yet the effect transferred to other languages, including Russian, French, Hindi, and Arabic.
  • Resilience without answer choices: even in an open-ended format without A/B/C multiple-choice hints, the model names a person on ambiguous questions in only 8.1% of cases, down from 61.5% for the base model.

What you can do

  • Reproduce debiasing experiments: evaluate how tiny-aya-global behaves on BBQ and MBBQ benchmarks (datasets designed to measure social stereotypes in question-answering systems).
  • Use it as an SFT tuning reference: take this LoRA configuration (rank 16, 1,412 rows) as a starting point to train small models to abstain when context is missing.

Example

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

base = "CohereLabs/tiny-aya-global"
tokenizer = AutoTokenizer.from_pretrained(base)
model = AutoModelForCausalLM.from_pretrained(base, dtype=torch.bfloat16)
model = PeftModel.from_pretrained(model, "vincentnkq/tiny-aya-global-attribution-lora")
Read moreDetails
Benchmarks: twin accuracy on the English BBQ test jumped from 34.7% to 92.7% (+58.0 percentage points); on the machine-translated Russian version, it reached 86.9% with only 4.8% false attributions.
Training: LoRA rank 16, alpha 32, dropout 0.05 (applied to q, k, v, o, gate, up, and down_proj modules), 3 epochs (267 steps), lr 0.0002, bfloat16; took 37 minutes on a single L4 GPU ($0.49).
Software and limitations: tested on transformers 5.22.1 and peft 0.21.2; this is a research artifact, not a general-purpose safety filter or universal hallucination guard for other task types.
Discuss Telegram 0 14

Will it run?

Runs in BF16

Fits without quantisation.

  • BF16weights 6.4 GB · ready files7.5 GB
  • FP8 / INT8recommendedweights 3.2 GB4.1 GB
  • 4-bitweights 1.9 GB2.6 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

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.

    # vincentnkq/tiny-aya-global-attribution-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-global --local-dir ~/models/tiny-aya-global
    hf download vincentnkq/tiny-aya-global-attribution-lora --local-dir ~/models/tiny-aya-global-attribution-lora
    # The model is in ~/models. How to run it is in the model card (link above).
    Add more LoRAs to tiny-aya-global
  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-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. tiny-aya-global-attribution-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

vincentnkq/tiny-aya-global-attribution-lora
Author
vincentnkq
Category
Other
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