mistral7b-de-mixed-bf16

mistral7b-de-mixed-bf16

Mistral-7B-v0.1 adapted to German as part of our study on efficient language adaptation: "Language Adaptation on a Tight Academic Compute Budget: Tokenizer Swapping Works and Pure bfloat16 Is Enough".

Code: https://github.com/konstantinjdobler/tight-budget-llm-adaptation

Paper: https://openreview.net/forum?id=VYfJaHeVod

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("konstantindobler/mistral7b-de-mixed-bf16")
model = AutoModelForCausalLM.from_pretrained("konstantindobler/mistral7b-de-mixed-bf16")

# Use model and tokenizer as usual

Details

The model is based on Mistral-7B-v0.1 and was adapted to German. The original tokenizer was kept. The model was then trained on 8 billion German tokens from oscar-corpus/OSCAR-2301 with mixed precision (bfloat16). More details and hyperparameters can be found in the paper.

Disclaimer

The web-scale dataset used for pretraining and tokenizer training (oscar-corpus/OSCAR-2301) might contain personal and sensitive information. Such behavior needs to be assessed carefully before any real-world deployment of the models.

Citation

Please cite as follows:

@inproceedings{dobler2024language,
    title={Language Adaptation on a Tight Academic Compute Budget: Tokenizer Swapping Works and Pure bfloat16 Is Enough},
    author={Konstantin Dobler and Gerard de Melo},
    booktitle={2nd Workshop on Advancing Neural Network Training: Computational Efficiency, Scalability, and Resource Optimization (WANT@ICML 2024)},
    year={2024},
    url={https://openreview.net/forum?id=VYfJaHeVod}
}

Acknowledgements

The project on which this model is based was funded by the Federal Ministry of Education and Research under the funding code "KI-Servicezentrum Berlin-Brandenburg" 01IS22092. Responsibility for the content of this publication remains with the author.