---
license: apache-2.0
library_name: peft
tags:
- alignment-handbook
- dpo
---

<p align="center" style="margin:0;padding:0">
<img src="8.PNG" alt="Reynaerde" width="800" style="margin-left:'auto' margin-right:'auto'/>
</p>



<div style="margin:auto; text-align:center">
<h1 style="margin-bottom: 0">Reynaerde 7B Chat</h1>
<em>A conversational model for Dutch, based on Mistral v0.3 Instruct</em>
</div>






This model is a fine-tuned version of TODO on [ReBatch/ultrafeedback_nl](https://huggingface.co/datasets/ReBatch/ultrafeedback_nl). This is a combination of a translation of the [HuggingFaceH4/ultrafeedback_binarized](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized) dataset and the HQ samples from [BramVanroy's translation](https://huggingface.co/datasets/BramVanroy/ultra_feedback_dutch_cleaned). 



## Model description

This model is a Dutch chat model, originally developed from Mistral 7B v0.3 Instruct and further fine-tuned with QLoRA. It was first fine-tuned with SFT on a chat dataset and then with DPO on a feedback chat dataset.
## Intended uses & limitations

This model could still generate wrong, misleading, and potentially even offensive content. Use at your own risk. 
Use with Mistral's chat template (can be found in the tokenizer).

## Training procedure


This model was trained with QLoRa in bfloat16 with Flash Attention 2 on one A100 PCIe, using the DPO script from the [alignment handbook](https://github.com/huggingface/alignment-handbook/) on [RunPod](https://www.runpod.io/).

## Evaluation results

The model was evaluated using [scandeval](https://scandeval.com/dutch-nlg/). There are improvements in 4 out of 7 benchmarks compared to the Mistral-7B-v0.3-Instruct model on which it is based.

| Model| conll_nl | dutch_social | scala_nl | squad_nl | wiki_lingua_nl | mmlu_nl | hellaswag_nl |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:
Reynaerde-7B-Chat | 56.40 / 38.13 | 10.83 / 27.67 | 20.02 / 55.40 | 53.56 / 65.29 | 68.13 / 20.85 | 32.50 / 49.10 |  31.36 / 47.79
Mistral-7B-v0.3 | 57.08 / 42.65 | 14.05 / 39.13 | 8.08 / 43.07 | 45.57 / 55.20 | 62.28 /  16.46 | 20.39 / 40.03 | 13.28 / 34.13
Mistral-7B-v0.3-Instruct | 60.76 / 45.39 | 13.20 / 34.26 | 23.23 / 59.26 | 48.94 / 60.13 | 66.09 / 18.02 | 24.95 / 43.67 | 24.86 / 43.57


## Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 5e-06
- train_batch_size: 3
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 2
- total_train_batch_size: 6
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1

## Framework versions

- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.2.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1

## Model Developer

The Mistral-7B-v0.3-Instruct model, on which this model is based, was created by [Mistral AI](https://huggingface.co/mistralai).
The finetuning was done by [Julien Van den Avenne](https://huggingface.co/vandeju).