Small Language Models for Kazakh: models, tokenizers, and datasets for Kazakh language modeling.
Saken Tukenov
saken-tukenov
AI & ML interests
None yet
Recent Activity
updated
a model
about 8 hours ago
saken-tukenov/kazakh-moe-160M-A50M-domain
published
a model
about 8 hours ago
saken-tukenov/kazakh-moe-160M-A50M-domain
updated
a dataset
about 12 hours ago
saken-tukenov/kazakh-moe-domain-labeled
Organizations
Kazakh grammatical error correction — 13 progressive training runs on mT5-small and mT5-base.
-
saken-tukenov/kazakh-synthetic-gec-datasets
Preview • Updated • 21 -
saken-tukenov/gazeta-kazakh
Viewer • Updated • 74.1k • 14 -
saken-tukenov/kazakh-gec-mt5-small-run1-processed
Text Generation • 0.3B • Updated • 20 -
saken-tukenov/kazakh-gec-mt5-small-run2-processed-v2
Text Generation • 0.3B • Updated • 28
Small Language Models for Kazakh: models, tokenizers, and datasets for Kazakh language modeling.
Kazakh grammatical error correction — 13 progressive training runs on mT5-small and mT5-base.
-
saken-tukenov/kazakh-synthetic-gec-datasets
Preview • Updated • 21 -
saken-tukenov/gazeta-kazakh
Viewer • Updated • 74.1k • 14 -
saken-tukenov/kazakh-gec-mt5-small-run1-processed
Text Generation • 0.3B • Updated • 20 -
saken-tukenov/kazakh-gec-mt5-small-run2-processed-v2
Text Generation • 0.3B • Updated • 28
models
28
saken-tukenov/kazakh-moe-160M-A50M-domain
0.2B
•
Updated
saken-tukenov/kazakh-moe-200M-A50M
Text Generation
•
0.2B
•
Updated
saken-tukenov/kazakh-llama-50m-v2
50.6M
•
Updated
saken-tukenov/kazakh-gec-mt5-models
Updated
saken-tukenov/kazakh-gec-mt5-base-run13-finetune
Text Generation
•
0.6B
•
Updated
•
17
saken-tukenov/kazakh-gec-mt5-base-run12-kazsandra-new
Text Generation
•
0.6B
•
Updated
•
20
saken-tukenov/kazakh-gec-mt5-base-run11-kazsandra
Text Generation
•
0.6B
•
Updated
•
18
saken-tukenov/kazakh-gec-mt5-base-run10-hybrid-v1
Text Generation
•
0.6B
•
Updated
•
24
saken-tukenov/kazakh-gec-mt5-base-run9-grammar-balanced-v2
Text Generation
•
0.6B
•
Updated
•
17
saken-tukenov/kazakh-gec-mt5-base-run8-grammar-combined
Text Generation
•
0.6B
•
Updated
•
16
datasets
10
saken-tukenov/kazakh-moe-domain-labeled
Viewer
•
Updated
•
2.19M
saken-tukenov/kazakh-moe-instruction-sft
Viewer
•
Updated
•
10.1k
saken-tukenov/kazakh-clean-pretrain-v2
Viewer
•
Updated
•
1.02M
saken-tukenov/kazakh-clean-pretrain-text-v2
Viewer
•
Updated
•
19M
saken-tukenov/kazakh-balanced-gpt2-style
Viewer
•
Updated
•
480k
•
22
saken-tukenov/gazeta-kazakh
Viewer
•
Updated
•
74.1k
•
14
saken-tukenov/kazakh-llama-50m-tokenized
Viewer
•
Updated
•
5.9M
•
33
saken-tukenov/kazakh-synthetic-gec-datasets
Preview
•
Updated
•
21
saken-tukenov/kazakh-clean-pretrain
Viewer
•
Updated
•
66.6k
saken-tukenov/kazakh-clean-pretrain-text
Viewer
•
Updated
•
78.7k