Instructions to use masakhane/m2m100_418M_en_zul_news with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use masakhane/m2m100_418M_en_zul_news with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("masakhane/m2m100_418M_en_zul_news") model = AutoModelForMultimodalLM.from_pretrained("masakhane/m2m100_418M_en_zul_news") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 10.0, | |
| "predict_bleu": 16.6351, | |
| "predict_gen_len": 50.006, | |
| "predict_loss": 2.330315113067627, | |
| "predict_runtime": 476.5803, | |
| "predict_samples": 998, | |
| "predict_samples_per_second": 2.094, | |
| "predict_steps_per_second": 0.21, | |
| "train_loss": 1.5844166957310268, | |
| "train_runtime": 1255.9196, | |
| "train_samples": 3500, | |
| "train_samples_per_second": 27.868, | |
| "train_steps_per_second": 2.787 | |
| } |