Dmitrii Kuzmin

ikkiren 's models 88

Sort:  Recently updated

ikkiren/llama-3.2-1b-c4-ru-12k-lora-fixed-ch20k

1B • Updated Mar 21

ikkiren/llama-3.2-1b-c4-ru-12k-lora-fixed-ch10k

1B • Updated Mar 20

ikkiren/llama-3.2-1b-c4-ru-12k-4-unfrozen-layers

1B • Updated Mar 16

ikkiren/llama-3.2-1b-c4-ru-12k-4-unfrozen-layers-ch58k

1B • Updated Mar 15

ikkiren/llama-3.2-1b-c4-ru-12k-4-unfrozen-layers-ch60k

1B • Updated Mar 15

ikkiren/llama-3.2-1b-c4-ru-12k-tail-replaced-reinit-fixed-3-epoch-ch64k

1B • Updated Mar 9

ikkiren/llama-3.2-1b-12k-tail-embed-reinit-fixed

1B • Updated Feb 27

ikkiren/llama-3.2-1b-c4-ru-12k-tail-replaced-reinit-fixed-ch64k

1B • Updated Feb 22 • 5

ikkiren/llama-3.2-1b-c4-ru-38k-tail-replaced-reinit

1B • Updated Feb 19

ikkiren/llama-3.2-1b-c4-ru-38k-tail-replaced-reinit-ch66k

1B • Updated Feb 15

ikkiren/llama-3.2-1b-c4-ru-tail-replaced-reinit-continued

1B • Updated Feb 11

ikkiren/llama-3.2-1b-c4-ru-tail-replaced-reinit

1B • Updated Feb 7

ikkiren/llama-3.2-1b-c4-ru-tail-replaced

1B • Updated Feb 2

ikkiren/research_tokenizer

Updated Apr 21, 2025

ikkiren/TS_50k_8B

Text Generation • 8B • Updated Apr 3, 2025 • 9

ikkiren/llama3-8b-instruct-unified-reg-hn-200k

Updated Mar 22, 2025

ikkiren/research_merged_layer

Text Generation • 1B • Updated Mar 6, 2025 • 4

ikkiren/research

Text Generation • 1B • Updated Mar 3, 2025 • 6

ikkiren/TokenSubstitution_50k

8B • Updated Feb 8, 2025 • 4

ikkiren/llama-with-lm-head

8B • Updated Feb 3, 2025 • 4

ikkiren/TokenSubstitution

8B • Updated Jan 29, 2025 • 3

ikkiren/llama-no-lm-head

8B • Updated Jan 29, 2025 • 4

ikkiren/korean

8B • Updated Jan 29, 2025 • 5

ikkiren/TokenSubstitution_tokenizer_50k

Updated Jan 5, 2025

ikkiren/TokenSubstitution_tokenizer_25600

Updated Dec 27, 2024

ikkiren/TokenSubstitution_tokenizer_38400

Updated Dec 27, 2024

ikkiren/TokenSubstitution_tokenizer_32k

Updated Dec 27, 2024

ikkiren/TokenSubstitution_tokenizer

Updated Aug 27, 2024