# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("benjaminsul/fine_tuned_he_to_tanach")
model = AutoModelForSeq2SeqLM.from_pretrained("benjaminsul/fine_tuned_he_to_tanach", device_map="auto")Quick Links
fine_tuned_he_to_tanach
This model is a fine-tuned version of google/mt5-large on a dataset that contains verses from the Bible translated in modern Hebrew.
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 25
Model tree for benjaminsul/fine_tuned_he_to_tanach
Base model
google/mt5-large
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="benjaminsul/fine_tuned_he_to_tanach")