Translation
Transformers
PyTorch
Russian
Kabardian
t5
text2text-generation
text-generation-inference
Instructions to use anzorq/t5-v1_1-small-ru_kbd-cased with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use anzorq/t5-v1_1-small-ru_kbd-cased 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="anzorq/t5-v1_1-small-ru_kbd-cased")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("anzorq/t5-v1_1-small-ru_kbd-cased") model = AutoModelForSeq2SeqLM.from_pretrained("anzorq/t5-v1_1-small-ru_kbd-cased", device_map="auto") - Notebooks
- Google Colab
- Kaggle
YAML Metadata Error:"datasets[1]" with value "17753 Russian-Kabardian pairs of text" is not valid. If possible, use a dataset id from https://hf.co/datasets.
google/t5-v1_1-small
pretrained on anzorq/kbd-ru-1.67M-temp
fine-tuned on 17753 Russian-Kabardian word/sentence pairs
kbd text uses custom latin script for optimization reasons.
Translation input should start with 'ru->kbd: '.
Tokenizer: T5 sentencepiece, char, cased.
- Downloads last month
- 7