Instructions to use WindyTranslate/translate-mfe-en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use WindyTranslate/translate-mfe-en 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="WindyTranslate/translate-mfe-en")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("WindyTranslate/translate-mfe-en") model = AutoModelForSeq2SeqLM.from_pretrained("WindyTranslate/translate-mfe-en", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Promote lora build from WindstormLabs/translate-mfe-en, with attribution and change statement
f0150fb verified - Xet hash:
- 3d3b410ff8eb8a408d3ffc5e2b73d265c25fde7f73b84a10fc05d3c3c9c6f963
- Size of remote file:
- 681 kB
- SHA256:
- 89c7042a6f91ac9f48d884ab079a53358f1e3267dccbf327d3cc9b0120ee89d4
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.