Instructions to use akahana/tinybert-javanese with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use akahana/tinybert-javanese with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="akahana/tinybert-javanese")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("akahana/tinybert-javanese") model = AutoModelForMaskedLM.from_pretrained("akahana/tinybert-javanese", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.1400072934534502, | |
| "eval_loss": 6.242714881896973, | |
| "eval_runtime": 11.5498, | |
| "eval_samples": 3852, | |
| "eval_samples_per_second": 333.512, | |
| "eval_steps_per_second": 83.378, | |
| "perplexity": 514.2527529747575 | |
| } |