Fill-Mask
Transformers
Safetensors
Latin
xlm-roberta
medieval-latin
canon-law
domain-adaptation
legal-history
digital-humanities
Instructions to use mschonhardt/CanonBerta-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mschonhardt/CanonBerta-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="mschonhardt/CanonBerta-v1")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("mschonhardt/CanonBerta-v1") model = AutoModelForMaskedLM.from_pretrained("mschonhardt/CanonBerta-v1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer_diagnostics.json from mschonhardt/CanonBerta-v1: direct link, hf CLI and curl.
- Browser
- Download file 323 Bytes
-
https://huggingface.co/mschonhardt/CanonBerta-v1/resolve/main/tokenizer_diagnostics.json
- Command line
-
hf download hf://mschonhardt/CanonBerta-v1/tokenizer_diagnostics.json
-
curl -L -o tokenizer_diagnostics.json https://huggingface.co/mschonhardt/CanonBerta-v1/resolve/main/tokenizer_diagnostics.json
323 Bytes
| { | |
| "mode": "pretokenized", | |
| "sampled_sequences": 20000, | |
| "total_sequences": 483367, | |
| "unk_rate": 3.4e-05, | |
| "total_unk_tokens": 340, | |
| "seq_len": { | |
| "mean": 494.9529, | |
| "p50": 512.0, | |
| "p95": 512.0, | |
| "max": 512 | |
| }, | |
| "share_over_max_seq_len": 0.0, | |
| "starts_with_bos_rate": 1.0, | |
| "ends_with_eos_rate": 1.0 | |
| } |