Mikhail's picture

Mikhail

RefalMachine

·

RefalMachine

AI & ML interests

NLP

Recent Activity

liked a dataset about 7 hours ago

lmarena/ruarena-user-preference-7k

updated a dataset 2 days ago

RefalMachine/ruadapt_hybrid_instruct

published a dataset 2 days ago

RefalMachine/ruadapt_hybrid_instruct

View all activity

Organizations

RefalMachine 's models 180

RefalMachine/ruadapt_qwen2.5_3B_ext_u48_instruct_v4

Text Generation • 3B • Updated Dec 31, 2024 • 1.15k • 28

RefalMachine/RuadaptQwen2.5-Coder-1.5B-instruct_v1

2B • Updated Nov 15, 2024 • 3

RefalMachine/RuadaptQwen2.5-Coder-1.5B-instruct_v2

2B • Updated Nov 15, 2024 • 3

RefalMachine/ruadapt_qwen2.5_3B_ext_u32_instruct_v3

3B • Updated Oct 17, 2024 • 2

RefalMachine/ruadapt_qwen2.5_3B_ext_u48_full_lr5e4_peft_mlp_32_32_bs256

Updated Oct 16, 2024 • 2

RefalMachine/ruadapt_qwen2.5_3B_ext_u48_full_lr3e4_peft_bs256_mlp

Updated Oct 16, 2024 • 2

RefalMachine/ruadapt_qwen2.5_3B_ext_u48_full_lr5e4_peft_bs256

Updated Oct 16, 2024 • 1

RefalMachine/ruadapt_qwen2.5_3B_ext_u48_full_lr3e4_peft_bs256_v2

Updated Oct 15, 2024 • 1

RefalMachine/ruadapt_qwen2.5_3B_ext_u48_full_lr1e4_peft_bs256_v2

Updated Oct 15, 2024 • 1

RefalMachine/ruadapt_qwen_2.5_3B_ext_u32_lep_ft_sft_kto_v2

3B • Updated Oct 15, 2024 • 3

RefalMachine/ruadapt_qwen2.5_3B_ext_u48_full_lr1e4_peft_bs256

Updated Oct 15, 2024 • 1

RefalMachine/ruadapt_qwen2.5_3B_ext_u48_full_lr5e4_bs256

Text Generation • 3B • Updated Oct 15, 2024 • 3

RefalMachine/ruadapt_qwen2.5_3B_ext_u48_full_lr3e4_bs256

Text Generation • 3B • Updated Oct 14, 2024 • 6

RefalMachine/ruadapt_qwen2.5_3B_u48_full_lr3e4_bs256

3B • Updated Oct 14, 2024 • 2

RefalMachine/ruadapt_qwen2.5_3B_u48_mean_init

3B • Updated Oct 14, 2024 • 3

RefalMachine/ruadapt_qwen2.5_3B_ext_u48_mean_init

3B • Updated Oct 14, 2024 • 3 • 1

RefalMachine/ruadapt_qwen_2.5_3B_ext_u32_lep_ft_sft_kto

3B • Updated Oct 13, 2024 • 3

RefalMachine/ruadapt_qwen2.5_3B_ext_cl100k_unigram_32000_full_lr5e4_bs256

3B • Updated Oct 13, 2024 • 3

RefalMachine/ruadapt_qwen2.5_3B_unigram_32000_full_lr5e4_bs256

3B • Updated Oct 12, 2024 • 4

RefalMachine/ruadapt_qwen2.5_3B_ext_cl100k_bpe_32000_full_lr5e4_bs256

3B • Updated Oct 12, 2024 • 3

RefalMachine/ruadapt_qwen2.5_3B_ext_cl100k_bpe_32000_full_lr5e4_2k_bs256

3B • Updated Oct 11, 2024 • 3

RefalMachine/ruadapt_qwen2.5_3B_ext_cl100k_bpe_32000_full_lr3e4_2k_bs256

3B • Updated Oct 11, 2024 • 3

RefalMachine/ruadapt_qwen2.5_3B_ext_cl100k_bpe_32000_full_lr2e4_2k_bs256

3B • Updated Oct 11, 2024 • 3

RefalMachine/ruadapt_qwen2.5_3B_unigram_32000_full_lr3e4_bs256

3B • Updated Oct 10, 2024 • 3

RefalMachine/ruadapt_qwen2.5_3B_bpe_32000_full_lr3e4_bs256

3B • Updated Oct 10, 2024 • 3 • 1

RefalMachine/ruadapt_qwen2.5_3B_ext_cl100k_unigram_32000_full_lr3e4_bs256

3B • Updated Oct 10, 2024 • 3

RefalMachine/ruadapt_qwen2.5_3B_ext_cl100k_bpe_32000_full_lr3e4_bs256

3B • Updated Oct 10, 2024 • 3

RefalMachine/ruadapt_qwen2.5_3B_ext_cl100k_unigram_32000_full_lr2e4_bs256

3B • Updated Oct 10, 2024 • 3

RefalMachine/ruadapt_qwen2.5_3B_unigram_32000_full_lr2e4_bs256

3B • Updated Oct 10, 2024 • 3

RefalMachine/ruadapt_qwen2.5_3B_ext_cl100k_bpe_32000_full_lr2e4_bs256

3B • Updated Oct 10, 2024 • 3