Instructions to use Hartunka/tiny_bert_rand_100_v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Hartunka/tiny_bert_rand_100_v1 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, DistilBertForLDAMaskedLM tokenizer = AutoTokenizer.from_pretrained("Hartunka/tiny_bert_rand_100_v1") model = DistilBertForLDAMaskedLM.from_pretrained("Hartunka/tiny_bert_rand_100_v1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download eval_results.json from Hartunka/tiny_bert_rand_100_v1: direct link, hf CLI and curl.
- Browser
- Download file 266 Bytes
-
https://huggingface.co/Hartunka/tiny_bert_rand_100_v1/resolve/main/eval_results.json
- Command line
-
hf download hf://Hartunka/tiny_bert_rand_100_v1/eval_results.json
-
curl -L -o eval_results.json https://huggingface.co/Hartunka/tiny_bert_rand_100_v1/resolve/main/eval_results.json
266 Bytes
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.15251172515115557, | |
| "eval_loss": 10.893685340881348, | |
| "eval_runtime": 0.7516, | |
| "eval_samples": 479, | |
| "eval_samples_per_second": 637.341, | |
| "eval_steps_per_second": 6.653, | |
| "perplexity": 53835.33639612944 | |
| } |