Mikhail's picture

Mikhail

RefalMachine

·

RefalMachine

AI & ML interests

NLP

Recent Activity

liked a model 8 days ago

t-tech/T-pro-it-2.1

liked a model 8 days ago

t-tech/T-lite-it-2.1

upvoted a paper 20 days ago

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

View all activity

Organizations

RefalMachine 's models 184

RefalMachine/llama3_extended_darulm_20_05_24_part1-2_64000_bpe_full_lr1e4_bs256

Text Generation • 8B • Updated Jul 14, 2024 • 5

RefalMachine/llama3_darulm_20_05_24_part1-2_128000_unigram_full_lr1e4_bs256

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

RefalMachine/llama3_darulm_20_05_24_part1-2_128000_bpe_full_lr1e4_bs256

Text Generation • 8B • Updated Jul 14, 2024 • 4

RefalMachine/openchat-3.5-0106__eval_bs_experiments

Updated Jul 13, 2024

RefalMachine/Meta-Llama-3-8B-Instruct_eval_bs_experiments

Updated Jul 13, 2024

RefalMachine/saiga_llama3_8b_v7_eval

Updated Jul 12, 2024

RefalMachine/Qwen2-7B-Instruct_eval

Updated Jul 12, 2024

RefalMachine/openchat-3.5-0106_eval

Updated Jul 12, 2024

RefalMachine/gemma-2-9b-it

Updated Jul 12, 2024

RefalMachine/Meta-Llama-3-8B-Instruct_eval

Updated Jul 12, 2024

RefalMachine/llama3_cut_extended_darulm_20_05_24_part1-2_64000_64000_bpe_part1_lr2e5_bs256

Text Generation • 8B • Updated Jul 11, 2024 • 6

RefalMachine/llama3_cut_extended_darulm_20_05_24_part1-2_64000_64000_bpe_part1_lr5e5_bs256

Text Generation • 8B • Updated Jul 9, 2024 • 5

RefalMachine/llama3_cut_extended_darulm_20_05_24_part1-2_64000_64000_bpe_part1_lr2e4_bs256

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

RefalMachine/llama3_cut_extended_darulm_20_05_24_part1-2_64000_64000_bpe_part1_lr1e4_bs256

Text Generation • 8B • Updated Jul 8, 2024 • 4

RefalMachine/mistral_darulm_20_05_24_part1-2_32000_unigram_part1-2_lr1e4_bs256

Updated Jul 8, 2024

RefalMachine/llama3_extended_darulm_20_05_24_part1-2_64000_bpe_part1_lr2e5_bs256

Text Generation • 8B • Updated Jul 8, 2024 • 5

RefalMachine/llama3_cut_extended_darulm_20_05_24_part1-2_64000_64000_bpe_mean_init_03_07_24

Text Generation • 8B • Updated Jul 8, 2024 • 5

RefalMachine/mistral_extended_darulm_20_05_24_part1-2_32000_bpe_part1-2_lr1e4_bs256

Text Generation • 7B • Updated Jul 8, 2024 • 3

RefalMachine/mistral_darulm_20_05_24_part1-2_32000_bpe_part1-2_lr1e4_bs256

Text Generation • 7B • Updated Jul 8, 2024 • 5

RefalMachine/llama3_extended_darulm_20_05_24_part1-2_64000_bpe_part1_lr5e5_bs256

Text Generation • 8B • Updated Jul 7, 2024 • 5

RefalMachine/llama3_extended_darulm_20_05_24_part1-2_64000_bpe_part1_lr1e4_bs256

Text Generation • 8B • Updated Jul 6, 2024 • 3

RefalMachine/llama3_extended_darulm_20_05_24_part1-2_64000_bpe_part1_lr2e4_bs256

Text Generation • 8B • Updated Jul 6, 2024 • 5

RefalMachine/mistral_extended_darulm_20_05_24_part1-2_32000_bpe_full_lr1e4_bs256

Text Generation • 7B • Updated Jul 5, 2024 • 4

RefalMachine/mistral_darulm_20_05_24_part1-2_32000_unigram_full_lr1e4_bs256

Text Generation • 7B • Updated Jul 5, 2024 • 6

RefalMachine/mistral_darulm_20_05_24_part1-2_32000_bpe_full_lr1e4_bs256

Text Generation • 7B • Updated Jul 5, 2024 • 6

RefalMachine/llama3_extended_darulm_20_05_24_part1-2_64000_bpe_mean_init_03_07_24

Text Generation • 8B • Updated Jul 5, 2024 • 5

RefalMachine/mistral_extended_darulm_20_05_24_part1-2_32000_bpe_part1_lr2e5_bs256

Text Generation • 7B • Updated Jul 4, 2024 • 5

RefalMachine/mistral_extended_darulm_20_05_24_part1-2_32000_bpe_part1_lr2e4_bs256

Text Generation • 7B • Updated Jul 4, 2024 • 6

RefalMachine/llama3_darulm_20_05_24_part1-2_128000_bpe_part1_lr2e4_bs256

Text Generation • 8B • Updated Jul 4, 2024 • 5

RefalMachine/llama3_darulm_20_05_24_part1-2_128000_bpe_part1_lr2e5_bs256

Text Generation • 8B • Updated Jul 4, 2024 • 5