Modelpublic

hamishivi/tulu-2-multitask-rrmax-326k-sft

sourceHugging Faceupdated 2y agoView on Hugging Face

1likes25downloads

Model Card

RDS+ Multitask Tulu 2 326k

This is a model trained on 326k samples selected by RDS+ for multiple tasks at once from the Tulu 2 unfiltered dataset. For more details, please see the paper Practical Large-Scale Data Selection for Instruction Tuning and associated codebase.

This model outperforms the original Tulu 2 SFT model by selecting more targeted data from the same original pool of data.

.Model description

—Model type: A model instruction-tuned on data selected from Tulu 2 unfiltered.
—Language(s) (NLP): English
—License: Llama 2 models are licensed under the Llama 2 license. A copy of this and a notice file can be found in this repository.
—Finetuned from model: meta-llama/Llama-2-7b-hf

Model Sources

—Repository: https://github.com/hamishivi/automated-instruction-selection
—Dataset: Data used to train this model can be found here.
—Model Family: The collection of related models can be found here.

Results

For more results and analysis, please see our paper.

Method	MMLU	GSM8k	BBH	TydiQA	Codex	Squad	AlpacaEval	Average
Rand. (unbal)	52.2	18.0	44.5	55.3	25.7	81.5	33.9	44.5
Rand. (bal)	51.5	21.8	45.1	50.7	32.2	87.9	43.2	47.5
Top-PPL	49.1	10.5	39.4	49.4	21.6	80.3	5.6	36.6
Mid-PPL	53.1	13.3	42.8	52.4	20.3	86.2	20.7	41.3
Embed (GTR)	49.9	32.8	44.6	54.4	30.4	88.4	35.7	48.0
Embed (NV)	50.6	28.7	44.4	56.0	30.4	89.1	17.9	45.3
IFD	45.7	21.8	41.2	39.5	27.7	17.0	57.4	35.7
Tulu 2	50.0	22.7	45.1	54.0	33.1	86.9	54.4	49.5
RDS+ (this model)	50.2	35.2	44.7	56.3	35.1	89.0	45.6	50.9
RDS+ - Wildchat	50.9	24.8	43.6	57.3	31.1	87.3	39.3	47.8
RDS+ - Arena Hard	48.1	36.2	43.9	51.8	31.8	81.3	59.4	50.4

Input Format

The model is trained to use the following format (note the newlines):

<|user|>
Your message here!
<|assistant|>

For best results, format all inputs in this manner. Make sure to include a newline after `<|assistant|>`, this can affect generation quality quite a bit. We have included a chat template in the tokenizer implementing this template.

Bias, Risks, and Limitations

These models have not been aligned to generate safe completions, so the model can produce problematic outputs (especially when prompted to do so).

Training hyperparameters

The following hyperparameters were used during training:

—learning_rate: 2e-05
—totaltrainbatch_size: 128
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: linear
—lrschedulerwarmup_ratio: 0.03
—num_epochs: 2.0

Citation

If you find this model or data is useful in your work, please cite it with:

@misc{ivison2025data,
      title={{Practical Large-Scale Data Selection for Instruction Tuning}}, 
      author={{Hamish Ivison and Muru Zhang and Faeze Brahman and Pang Wei Koh and Pradeep Dasigi}}
      year={2025},
      eprint={2503.01807},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2503.01807}
}