--- license: apache-2.0 datasets: - argilla/distilabel-intel-orca-dpo-pairs language: - en tags: - distilabel - dpo - rlaif - rlhf - merge - mergekit --- # ⚗️ distilabeled Marcoro14 7B Slerp
## Introduction This model is a new DPO fine-tune of our new open dataset [argilla/distilabel-intel-orca-dpo-pairs](https://huggingface.co/datasets/argilla/distilabel-intel-orca-dpo-pairs), on the [mlabonne/Marcoro14-7B-slerp](https://huggingface.co/mlabonne/Marcoro14-7B-slerp) model. You can find more information of the "distilabeled" dataset used at this repo [argilla/distilabeled-Hermes-2.5-Mistral-7B](https://huggingface.co/argilla/distilabeled-Hermes-2.5-Mistral-7B/blob/main/README.md#introduction), and visit [distilabel](https://github.com/argilla-io/distilabel). ## Training details As we did with [Notus](https://argilla.io/blog/notus7b/), we wanted a reproducible recipe to test the impact of data quality. And we're lucky to have so many amazing folks in the open community contributing reproducible, easy-to-use training scripts and recipes. This time, [Maxime Labonne](https://twitter.com/maximelabonne) had shared a [Colab](https://colab.research.google.com/drive/15iFBr1xWgztXvhrj5I9fBv20c7CFOPBE?usp=sharing) to fine-tune OpenHermes with DPO and the original Intel's dataset, perfect! We just updated the base model to [mlabonne/Marcoro14-7B-slerp](https://huggingface.co/mlabonne/Marcoro14-7B-slerp), and applied the same dataset recipe we used for [argilla/distilabeled-Hermes-2.5-Mistral-7B](https://huggingface.co/argilla/distilabeled-Hermes-2.5-Mistral-7B/blob/main/README.md#introduction): ```python from datasets import load_dataset # Instead of this: # dataset = load_dataset("Intel/orca_dpo_pairs", split="train") # we did this dataset = load_dataset("argilla/distilabel-intel-orca-dpo-pairs", split="train") dataset = dataset.filter( lambda r: r["status"] != "tie" and r["chosen_score"] >= 8 and not r["in_gsm8k_train"] ) ``` ## Benchmark results For benchmarking we used the famous "Nous" or "Teknium" benchmark. You can find below an overview, including our first experiment with a less ambitious dataset filtering (removing ties and `score>5`). For running the benchmark we used another awesome contribution from Maxime: [LLM AutoEval](https://github.com/mlabonne/llm-autoeval), check it out! | Model |AGIEval|GPT4ALL|TruthfulQA|Bigbench|Average| |-------------------------|------:|------:|---------:|-------:|------:| |[argilla/distilabeled-Marcoro14-7B-slerp](https://huggingface.co/argilla/distilabeled-Marcoro14-7B-slerp)| **45.4**| **76.47**| **65.46**| **47.19**| **58.63**| |[Marcoro14-7B-slerp](https://huggingface.co/mlabonne/Marcoro14-7B-slerp) | 44.66| 76.24| 64.15| 45.64| 57.67| |[argilla/distilabeled-Hermes-2.5-Mistral-7B](https://huggingface.co/argilla/distilabeled-Hermes-2.5-Mistral-7B) | 44.64 | 73.35 | 55.96 | 42.21 | 54.04 | ### Training Hardware We used 1 x A100 80GB in runpod for less than 1 hour. ## Acknowledgements We'd like to thank the amazing open community and in particular: * The Intel team for publishing a great open dataset and show how well it worked in the first place * Teknium and NousResearch for their awesome work and models. * Maxime for sharing such great resources.