Mikhail's picture

Mikhail

RefalMachine

·

RefalMachine

AI & ML interests

NLP

Recent Activity

liked a model 4 days ago

t-tech/T-pro-it-2.1

liked a model 4 days ago

t-tech/T-lite-it-2.1

upvoted a paper 15 days ago

T-pro 2.0: An Efficient Russian Hybrid-Reasoning Model and Playground

View all activity

Organizations

RefalMachine 's models 184

RefalMachine/ruadapt_qwen2.5_3B_ext_cl100k_bpe_32000_full_lr3e4_bs256

3B • Updated Oct 10, 2024 • 8

RefalMachine/ruadapt_qwen2.5_3B_ext_cl100k_unigram_32000_full_lr2e4_bs256

3B • Updated Oct 10, 2024 • 6

RefalMachine/ruadapt_qwen2.5_3B_unigram_32000_full_lr2e4_bs256

3B • Updated Oct 10, 2024 • 5

RefalMachine/ruadapt_qwen2.5_3B_ext_cl100k_bpe_32000_full_lr2e4_bs256

3B • Updated Oct 10, 2024 • 4

RefalMachine/ruadapt_qwen2.5_3B_bpe_32000_full_lr2e4_bs256

3B • Updated Oct 9, 2024 • 7

RefalMachine/ruadapt_qwen2.5_3B_darulm_bpe_64000_full_lr3e4_bs256

3B • Updated Oct 9, 2024 • 7

RefalMachine/ruadapt_qwen2.5_3B_ext_cl100k_unigram_32000_mean_init

3B • Updated Oct 9, 2024 • 5

RefalMachine/ruadapt_qwen2.5_3B_ext_cl100k_bpe_32000_mean_init

3B • Updated Oct 9, 2024 • 8

RefalMachine/ruadapt_qwen2.5_3B_unigram_32000_mean_init

3B • Updated Oct 9, 2024 • 7

RefalMachine/ruadapt_qwen2.5_3B_bpe_32000_mean_init

3B • Updated Oct 9, 2024 • 7

RefalMachine/ruadapt_qwen2.5_3B_darulm_cl100k_extended_u60k_full_lr3e4_bs256

3B • Updated Oct 9, 2024 • 6

RefalMachine/ruadapt_qwen2.5_3B_darulm_cl100k_extended_u60k_full_lr2e4_bs256

3B • Updated Oct 8, 2024 • 7

RefalMachine/ruadapt_qwen2.5_3B_darulm_cl100k_extended_u60k_mean_init

3B • Updated Oct 8, 2024 • 6

RefalMachine/ruadapt_qwen2.5_3B_darulm_bpe_128000_full_lr2e4_bs256

3B • Updated Oct 8, 2024 • 4

RefalMachine/ruadapt_qwen2.5_3B_darulm_unigram_128000_full_lr2e4_bs256

3B • Updated Oct 8, 2024 • 6

RefalMachine/ruadapt_qwen2.5_3B_darulm_unigram_128000_mean_init

3B • Updated Oct 7, 2024 • 7

RefalMachine/ruadapt_qwen2.5_3B_darulm_bpe_128000_mean_init

3B • Updated Oct 7, 2024 • 7

RefalMachine/ruadapt_qwen2.5_3B_darulm_bpe_64000_full_lr2e4_bs256

3B • Updated Oct 7, 2024 • 5

RefalMachine/ruadapt_qwen2.5_3B_darulm_bpe_64000_mean_init

3B • Updated Oct 7, 2024 • 5

RefalMachine/ruadapt_llama3_instruct_lep_saiga_kto_ablitirated

8B • Updated Aug 30, 2024 • 17 • 2

RefalMachine/ruadapt_mistral_7b_openchat_extended_lep_ft

7B • Updated Aug 22, 2024 • 8

RefalMachine/ruadapt_llama3_8b_instruct_extended_lep_ft

8B • Updated Aug 22, 2024 • 12 • 4

RefalMachine/Meta-Llama-3-8B_eval

Updated Aug 15, 2024

RefalMachine/llama3_darulm_20_05_24_part1-2_128000_unigram_full_lr2e4_bs256_v2

Text Generation • 8B • Updated Jul 18, 2024 • 11

RefalMachine/llama3_darulm_20_05_24_part1-2_128000_bpe_full_lr2e4_bs256_v2

Text Generation • 8B • Updated Jul 18, 2024 • 8

RefalMachine/llama3_extended_darulm_20_05_24_part1-2_64000_bpe_full_lr2e4_bs256

Text Generation • 8B • Updated Jul 17, 2024 • 11

RefalMachine/llama3_darulm_20_05_24_part1-2_128000_bpe_full_lr2e4_bs256

Text Generation • 8B • Updated Jul 17, 2024 • 7

RefalMachine/llama3_darulm_20_05_24_part1-2_128000_unigram_full_lr2e4_bs256

Text Generation • 8B • Updated Jul 17, 2024 • 9

RefalMachine/llama3_cut_extended_darulm_20_05_24_part1-2_64000_64000_bpe_full_lr2e4_bs256

Text Generation • 8B • Updated Jul 14, 2024 • 10

RefalMachine/llama3_cut_extended_darulm_20_05_24_part1-2_64000_64000_bpe_full_lr1e4_bs256

Text Generation • 8B • Updated Jul 14, 2024 • 10