Instructions to use Helsinki-NLP/opus-mt-eu-es with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Helsinki-NLP/opus-mt-eu-es 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="Helsinki-NLP/opus-mt-eu-es")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-eu-es") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-eu-es", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download generation_config.json from Helsinki-NLP/opus-mt-eu-es: direct link, hf CLI and curl.
- Browser
- Download file 293 Bytes
-
https://huggingface.co/Helsinki-NLP/opus-mt-eu-es/resolve/main/generation_config.json
- Command line
-
hf download hf://Helsinki-NLP/opus-mt-eu-es/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/Helsinki-NLP/opus-mt-eu-es/resolve/main/generation_config.json
293 Bytes
| { | |
| "bad_words_ids": [ | |
| [ | |
| 58059 | |
| ] | |
| ], | |
| "bos_token_id": 0, | |
| "decoder_start_token_id": 58059, | |
| "eos_token_id": 0, | |
| "forced_eos_token_id": 0, | |
| "max_length": 512, | |
| "num_beams": 4, | |
| "pad_token_id": 58059, | |
| "renormalize_logits": true, | |
| "transformers_version": "4.32.0.dev0" | |
| } | |