Kazakh-to-Russian translation
According to the model card, the model translates from Kazakh to Russian using a T5-based configuration.
Open Source Model Profile · deepvk
kazRush-kk-ru
kazRush-kk-ru is a deepvk T5 translation model from Kazakh to Russian. Captured metadata reports about 197M parameters under Apache-2.0.
- Publisher
- deepvk
- Task
- translation
- Model type
- t5
- License
- apache-2.0
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
kazRush-kk-ru is published by deepvk as a T5 translation model from Kazakh to Russian. The captured configuration identifies T5ForConditionalGeneration with model type t5, and Safetensors metadata reports 196,967,936 parameters. The model card describes training with randomly initialized weights on open-source parallel data under Apache-2.0.
Recorded capabilities
Transformers usage path
The model card says sentencepiece is required and documents Transformers Seq2Seq and pipeline usage.
Documented multi-source training data
According to the model card, training pairs came from OPUS Corpora at 718K, kazparc at 2,150K, wmt19 at 5,063K, and TIL at 4,403K, with cleaning and filtering steps.
Reported benchmark comparison
The model card reports 18.8 BLEU, 48.7 chrf, and 86.7 COMET for this 197M model alongside larger NLLB baselines.
Use cases in the source record
- Kazakh-to-Russian text translation using the card's documented Transformers Seq2Seq and pipeline workflows.
- Workflows where the sentencepiece dependency documented by the model card is installed for tokenization.
Limitations and unknowns
- No context-window value was extracted from this record.
- No current provider availability was verified; provider state is historical snapshot data.
- Training and benchmark details come from the publisher model card and were not independently verified by Ethen.
Source and provenance
Source: deepvk/kazRush-kk-ru
Captured: Unknown. Processed: 2026-09-07T19:34:43.637735+00:00.
kazRush-kk-ru kazRush-kk-ru is a translation model for translating from Kazakh to Russian. The model was trained with randomly initialized weights based on the T5 configuration on the available open-source parallel data. Usage Using the model requires sentencepiece library to be installed. After installing necessary dependencies the model can be run with the following code: from transformers import AutoModelForSeq2SeqLM, AutoTokenizer import torch device = "cuda" if torch.cuda.is_available() else "cpu" model = AutoModelForSeq2SeqLM.from_pretrained( 'deepvk/kazRush-kk-ru' ).to(device) tokenizer = AutoTokenizer.from_pretrained( 'deepv…
F001F002F003F004F005F006F007F011F012F013F014F015F016