konstantindobler's picture
Upload README.md with huggingface_hub
2b1d5e7 verified
|
raw
history blame
No virus
2.17 kB
---
language: de
license: apache-2.0
datasets: oscar-corpus/OSCAR-2301
---
# mistral7b-de-tokenizer-swap-pure-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
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("konstantindobler/mistral7b-de-tokenizer-swap-pure-bf16")
model = AutoModelForCausalLM.from_pretrained("konstantindobler/mistral7b-de-tokenizer-swap-pure-bf16")
# Use model and tokenizer as usual
```
## Details
The model is based on [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) and was adapted to German.
The original tokenizer was replaced by a language-specific German tokenizer with a vocabulary of 32768 tokens. The new embeddings were initialized with [FOCUS](https://github.com/konstantinjdobler/focus).
The model was then trained on 8 billion German tokens from [oscar-corpus/OSCAR-2301](https://huggingface.co/oscar-corpus/OSCAR-2301) with pure bfloat16 precision (no mixed precision). More details and hyperparameters can be found [in the paper](https://openreview.net/forum?id=VYfJaHeVod).
## Disclaimer
The web-scale dataset used for pretraining and tokenizer training ([oscar-corpus/OSCAR-2301](https://huggingface.co/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:
```bibtex
@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}
}
```