Instructions to use g8a9/roberta-tiny-8l-10M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use g8a9/roberta-tiny-8l-10M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="g8a9/roberta-tiny-8l-10M")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("g8a9/roberta-tiny-8l-10M") model = AutoModelForMaskedLM.from_pretrained("g8a9/roberta-tiny-8l-10M", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download all_results.json from g8a9/roberta-tiny-8l-10M: direct link, hf CLI and curl.
- Browser
- Download file 445 Bytes
-
https://huggingface.co/g8a9/roberta-tiny-8l-10M/resolve/main/all_results.json
- Command line
-
hf download hf://g8a9/roberta-tiny-8l-10M/all_results.json
-
curl -L -o all_results.json https://huggingface.co/g8a9/roberta-tiny-8l-10M/resolve/main/all_results.json
445 Bytes
| { | |
| "epoch": 17.7, | |
| "eval_accuracy": 0.05156855736415957, | |
| "eval_loss": 7.338886260986328, | |
| "eval_runtime": 180.6703, | |
| "eval_samples": 24055, | |
| "eval_samples_per_second": 133.143, | |
| "eval_steps_per_second": 4.162, | |
| "perplexity": 1538.997117682623, | |
| "train_loss": 7.482659651812385, | |
| "train_runtime": 11122.8848, | |
| "train_samples": 24910, | |
| "train_samples_per_second": 223.953, | |
| "train_steps_per_second": 0.432 | |
| } |