Instructions to use masakhane/afrimt5_zul_en_news with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use masakhane/afrimt5_zul_en_news with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("masakhane/afrimt5_zul_en_news") model = AutoModelForMultimodalLM.from_pretrained("masakhane/afrimt5_zul_en_news") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 10.0, | |
| "predict_bleu": 23.4124, | |
| "predict_gen_len": 38.6012, | |
| "predict_loss": 1.7577762603759766, | |
| "predict_runtime": 575.7491, | |
| "predict_samples": 998, | |
| "predict_samples_per_second": 1.733, | |
| "predict_steps_per_second": 0.174, | |
| "train_loss": 2.25457284109933, | |
| "train_runtime": 1155.5156, | |
| "train_samples": 3500, | |
| "train_samples_per_second": 30.29, | |
| "train_steps_per_second": 3.029 | |
| } |