ikkiren/research_tokenizer
Updated
Dmitrii Kuzmin
ikkiren
·
AI & ML interests
NLP
Organizations
None yet
models
15
ikkiren/TS_50k_8B
Text Generation
•
8B
•
Updated
•
2
ikkiren/llama3-8b-instruct-unified-reg-hn-200k
Updated
ikkiren/research_merged_layer
Text Generation
•
1B
•
Updated
•
1
ikkiren/research
Text Generation
•
1B
•
Updated
ikkiren/TokenSubstitution_50k
8B
•
Updated
•
1
ikkiren/llama-with-lm-head
8B
•
Updated
•
3
ikkiren/TokenSubstitution
8B
•
Updated
•
3
ikkiren/llama-no-lm-head
8B
•
Updated
ikkiren/korean
8B
•
Updated
•
3
datasets
8
ikkiren/bigdata_ds
Viewer
•
Updated
•
9.29M
•
2
ikkiren/research_dataset_small
Viewer
•
Updated
•
1.16M
•
9
ikkiren/research_dataset
Viewer
•
Updated
•
6.33M
•
134
ikkiren/big_tokenized_dataset_half
Viewer
•
Updated
•
2.47M
•
12
ikkiren/big_dataset
Viewer
•
Updated
•
5.09M
•
22
ikkiren/merged_instruct_refactor_tokenized_without_padding_cleaned
Viewer
•
Updated
•
1.08M
•
7
ikkiren/merged_instruct_refactor
Viewer
•
Updated
•
1.09M
•
11
ikkiren/ru_instruct_input_ids
Viewer
•
Updated
•
754k
•
15