Translation
Transformers
Safetensors
Arabic
English
marian
text2text-generation
darja
algerian-arabic
arabic-dialect
nmt
opus-mt
Instructions to use DarjaCore/darjacore-mt-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DarjaCore/darjacore-mt-base 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="DarjaCore/darjacore-mt-base")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("DarjaCore/darjacore-mt-base") model = AutoModelForSeq2SeqLM.from_pretrained("DarjaCore/darjacore-mt-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download source.spm from DarjaCore/darjacore-mt-base: direct link, hf CLI and curl.
- Browser
- Download file 915 kB
-
https://huggingface.co/DarjaCore/darjacore-mt-base/resolve/main/source.spm
- Command line
-
hf download hf://DarjaCore/darjacore-mt-base/source.spm
-
curl -L -o source.spm https://huggingface.co/DarjaCore/darjacore-mt-base/resolve/main/source.spm
915 kB
- Xet hash:
- 6aff753f2fb50c63cff544bf62f8c32de9786de0a24d7bc9fd6114bc0c9dadf7
- Size of remote file:
- 915 kB
- SHA256:
- fce8e7e41d2e9337d5176edc530bd900efd6d99f86153f755c88529796b67a65
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.