trans-tokenizers 0.1.0

Token translation for language models.

transtokenizers

Token translation for language models

• Documentation: https://ipieter.github.io/transtokenizer
• GitHub: https://github.com/LAGoM-NLP/transtokenizer
• PyPI: https://pypi.org/project/trans-tokenizers/
• Licence: MIT

Features

• TODO

Usage

from transtokenizers import transform_model
from transformers import AutoTokenizer, AutoModelForCausalLM

source_tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-v0.1")
target_tokenizer = AutoTokenizer.from_pretrained("pdelobelle/robbert-2023-dutch-base")

source_model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1")

target_model = transform_model(source_model, source_tokenizer=source_tokenizer, target_tokenizer=target_tokenizer)

Credits

If this repo was useful to you, please cite the following paper