Instructions to use Helsinki-NLP/opus-mt-en-iir with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Helsinki-NLP/opus-mt-en-iir 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-en-iir")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-en-iir") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-en-iir", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Download generation_config.json from Helsinki-NLP/opus-mt-en-iir: direct link, hf CLI and curl.
- Browser
- Download file 293 Bytes
-
https://huggingface.co/Helsinki-NLP/opus-mt-en-iir/resolve/refs%2Fpr%2F2/generation_config.json
- Command line
-
hf download hf://Helsinki-NLP/opus-mt-en-iir@refs/pr/2/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/Helsinki-NLP/opus-mt-en-iir/resolve/refs%2Fpr%2F2/generation_config.json
293 Bytes
| { | |
| "_from_model_config": true, | |
| "bad_words_ids": [ | |
| [ | |
| 62227 | |
| ] | |
| ], | |
| "bos_token_id": 0, | |
| "decoder_start_token_id": 62227, | |
| "eos_token_id": 0, | |
| "forced_eos_token_id": 0, | |
| "max_length": 512, | |
| "num_beams": 4, | |
| "pad_token_id": 62227, | |
| "transformers_version": "4.27.0.dev0" | |
| } | |