Instructions to use gaudi/opus-mt-ar-eo-ctranslate2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use gaudi/opus-mt-ar-eo-ctranslate2 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="gaudi/opus-mt-ar-eo-ctranslate2")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("gaudi/opus-mt-ar-eo-ctranslate2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from gaudi/opus-mt-ar-eo-ctranslate2: direct link, hf CLI and curl.
- Browser
- Download file 215 Bytes
-
https://huggingface.co/gaudi/opus-mt-ar-eo-ctranslate2/resolve/main/config.json
- Command line
-
hf download hf://gaudi/opus-mt-ar-eo-ctranslate2/config.json
-
curl -L -o config.json https://huggingface.co/gaudi/opus-mt-ar-eo-ctranslate2/resolve/main/config.json
215 Bytes
| { | |
| "add_source_bos": false, | |
| "add_source_eos": false, | |
| "bos_token": "<s>", | |
| "decoder_start_token": "</s>", | |
| "eos_token": "</s>", | |
| "layer_norm_epsilon": null, | |
| "unk_token": "<unk>", | |
| "model_type": "marian" | |
| } | |