Instructions to use jash33/mt5-en-to-hi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jash33/mt5-en-to-hi with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("jash33/mt5-en-to-hi") model = AutoModelForMultimodalLM.from_pretrained("jash33/mt5-en-to-hi") - Notebooks
- Google Colab
- Kaggle
mt5-en-to-hi
This model is a fine-tuned version of google/mt5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8281
- Bleu: 0.4263
- Gen Len: 18.5077
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 1.1543 | 1.0 | 12500 | 0.8676 | 0.2853 | 18.2712 |
| 1.0872 | 2.0 | 25000 | 0.8281 | 0.4263 | 18.5077 |
Framework versions
- Transformers 4.27.4
- Pytorch 1.13.0
- Datasets 2.1.0
- Tokenizers 0.13.2
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support