Instructions to use kredor/punctuate-all with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kredor/punctuate-all with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="kredor/punctuate-all")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("kredor/punctuate-all") model = AutoModelForTokenClassification.from_pretrained("kredor/punctuate-all", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Download special_tokens_map.json from kredor/punctuate-all: direct link, hf CLI and curl.
- Browser
- Download file 239 Bytes
-
https://huggingface.co/kredor/punctuate-all/resolve/main/special_tokens_map.json
- Command line
-
hf download hf://kredor/punctuate-all/special_tokens_map.json
-
curl -L -o special_tokens_map.json https://huggingface.co/kredor/punctuate-all/resolve/main/special_tokens_map.json
239 Bytes
| {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}} |