Translation
Transformers
Safetensors
Kabardian
Russian
marian
text2text-generation
kabardian
russian
circassian
low-resource
endangered-language
opus-mt
Instructions to use kubataba/kbd-ru-opus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kubataba/kbd-ru-opus 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="kubataba/kbd-ru-opus")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("kubataba/kbd-ru-opus") model = AutoModelForSeq2SeqLM.from_pretrained("kubataba/kbd-ru-opus", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download training_args.bin from kubataba/kbd-ru-opus: direct link, hf CLI and curl.
- Browser
- Download file 5.97 kB
-
https://huggingface.co/kubataba/kbd-ru-opus/resolve/main/training_args.bin
- Command line
-
hf download hf://kubataba/kbd-ru-opus/training_args.bin
-
curl -L -o training_args.bin https://huggingface.co/kubataba/kbd-ru-opus/resolve/main/training_args.bin
5.97 kB
- Xet hash:
- 1acbb9a8198bdfbcc6f9765e5282cbabb4e52ebdd22fd8cb0ff9059c678ab0dc
- Size of remote file:
- 5.97 kB
- SHA256:
- 2908782e210e710cc866c484b5b590d02df716c548626856e82d0cd0dd2c4f59
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.