Translation
Transformers
Safetensors
Toki Pona
Russian
marian
text2text-generation
Generated from Trainer
Instructions to use NetherQuartz/tatoeba-tok-ru with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NetherQuartz/tatoeba-tok-ru with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("translation", model="NetherQuartz/tatoeba-tok-ru")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("NetherQuartz/tatoeba-tok-ru") model = AutoModelForSeq2SeqLM.from_pretrained("NetherQuartz/tatoeba-tok-ru", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download special_tokens_map.json from NetherQuartz/tatoeba-tok-ru: direct link, hf CLI and curl.
- Browser
- Download file 79 Bytes
-
https://huggingface.co/NetherQuartz/tatoeba-tok-ru/resolve/main/special_tokens_map.json
- Command line
-
hf download hf://NetherQuartz/tatoeba-tok-ru/special_tokens_map.json
-
curl -L -o special_tokens_map.json https://huggingface.co/NetherQuartz/tatoeba-tok-ru/resolve/main/special_tokens_map.json
79 Bytes
| { | |
| "eos_token": "</s>", | |
| "pad_token": "<pad>", | |
| "unk_token": "<unk>" | |
| } | |