Instructions to use Hartunka/bert_base_rand_100_v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Hartunka/bert_base_rand_100_v2 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, DistilBertForLDAMaskedLM tokenizer = AutoTokenizer.from_pretrained("Hartunka/bert_base_rand_100_v2") model = DistilBertForLDAMaskedLM.from_pretrained("Hartunka/bert_base_rand_100_v2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download eval_results.json from Hartunka/bert_base_rand_100_v2: direct link, hf CLI and curl.
- Browser
- Download file 266 Bytes
-
https://huggingface.co/Hartunka/bert_base_rand_100_v2/resolve/main/eval_results.json
- Command line
-
hf download hf://Hartunka/bert_base_rand_100_v2/eval_results.json
-
curl -L -o eval_results.json https://huggingface.co/Hartunka/bert_base_rand_100_v2/resolve/main/eval_results.json
266 Bytes
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.15335932643950953, | |
| "eval_loss": 10.777741432189941, | |
| "eval_runtime": 1.0755, | |
| "eval_samples": 479, | |
| "eval_samples_per_second": 445.387, | |
| "eval_steps_per_second": 4.649, | |
| "perplexity": 47941.72223715789 | |
| } |