Edit model card

Model Card of instructionMBERTv1 for Bertology

A minimalistic multilingual instruction model with an already good analysed and pretrained encoder like mBERT. So we can research the Bertology with instruction-tuned models, look at the attention and investigate what happens to BERT embeddings during fine-tuning.

The training code is released at the instructionBERT repository. We used the Huggingface API for warm-starting BertGeneration with Encoder-Decoder-Models for this purpose.

Training parameters

  • base model: "google-bert/bert-base-multilingual-cased"
  • trained for 8 epochs
  • batch size of 16
  • 20000 warm-up steps
  • learning rate of 0.0001

Purpose of instructionMBERT

InstructionMBERT is intended for research purposes. The model-generated text should be treated as a starting point rather than a definitive solution for potential use cases. Users should be cautious when employing these models in their applications.

Downloads last month
1
Safetensors
Model size
207M params
Tensor type
F32
·

Dataset used to train Bachstelze/instructionMBERTv1