Instructions to use WhirlwindAI/Translate-25T with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use WhirlwindAI/Translate-25T 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="WhirlwindAI/Translate-25T")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("WhirlwindAI/Translate-25T") model = AutoModelForSeq2SeqLM.from_pretrained("WhirlwindAI/Translate-25T") - Notebooks
- Google Colab
- Kaggle
| { | |
| "_from_model_config": true, | |
| "decoder_start_token_id": 0, | |
| "eos_token_id": [ | |
| 1 | |
| ], | |
| "pad_token_id": 0, | |
| "transformers_version": "5.0.0" | |
| } | |