·
AI & ML interests
NLP
Organizations
RefalMachine/llama3_darulm_20_05_24_part1-2_128000_unigram_part1_lr2e5_bs256
Text Generation
• 8B • Updated • 11
RefalMachine/mistral_extended_darulm_20_05_24_part1-2_32000_bpe_part1_lr5e5_bs256
Text Generation
• 7B • Updated • 33
RefalMachine/mistral_extended_darulm_20_05_24_part1-2_32000_bpe_part1_lr1e4_bs256
Text Generation
• 7B • Updated • 33
RefalMachine/llama3_darulm_20_05_24_part1-2_128000_unigram_part1_lr5e5_bs256
Text Generation
• 8B • Updated • 9
RefalMachine/llama3_darulm_20_05_24_part1-2_128000_bpe_part1_lr1e4_bs256
Text Generation
• 8B • Updated • 9
RefalMachine/llama3_darulm_20_05_24_part1-2_128000_bpe_part1_lr5e5_bs256
Text Generation
• 8B • Updated • 10
RefalMachine/mistral_extended_darulm_20_05_24_part1-2_32000_bpe_mean_init_03_07_24
Text Generation
• 7B • Updated • 44
RefalMachine/mistral_darulm_20_05_24_part1-2_32000_bpe_part1_lr2e5_bs256
Text Generation
• 7B • Updated • 36
RefalMachine/mistral_darulm_20_05_24_part1-2_32000_unigram_part1_lr2e5_bs256
Text Generation
• 7B • Updated • 24
RefalMachine/llama3_darulm_20_05_24_part1-2_128000_unigram_part1_lr2e4_bs256
Text Generation
• 8B • Updated • 10
RefalMachine/mistral_darulm_20_05_24_part1-2_32000_unigram_part1_lr2e4_bs256
Text Generation
• 7B • Updated • 25
RefalMachine/llama3_darulm_20_05_24_part1-2_128000_unigram_part1_lr1e4_bs256
Text Generation
• 8B • Updated • 10
RefalMachine/mistral_darulm_20_05_24_part1-2_32000_unigram_part1_lr1e4_bs256
Text Generation
• 7B • Updated • 25
RefalMachine/mistral_darulm_20_05_24_part1-2_32000_unigram_part1_lr5e5_bs256
Text Generation
• 7B • Updated • 25
RefalMachine/mistral_darulm_20_05_24_part1-2_32000_bpe_part1_lr2e4_bs256
Text Generation
• 7B • Updated • 37
RefalMachine/mistral_darulm_20_05_24_part1-2_32000_bpe_part1_lr5e5_bs256
Text Generation
• 7B • Updated • 37
RefalMachine/mistral_darulm_20_05_24_part1-2_32000_bpe_part1_lr1e4_bs256
Text Generation
• 7B • Updated • 35
RefalMachine/llama3_darulm_20_05_24_part1-2_128000_bpe_mean_init_03_07_24
Text Generation
• 8B • Updated • 17
RefalMachine/llama3_darulm_20_05_24_part1-2_128000_unigram_mean_init_03_07_24
Text Generation
• 8B • Updated • 16
RefalMachine/mistral_darulm_20_05_24_part1-2_32000_unigram_mean_init_03_07_24
Text Generation
• 7B • Updated • 26
RefalMachine/mistral_darulm_20_05_24_part1-2_32000_bpe_test_pipeline_1k_steps
Text Generation
• 7B • Updated • 35
RefalMachine/mistral_darulm_20_05_24_part1-2_32000_bpe_mean_init_03_07_24
Text Generation
• 7B • Updated • 45
RefalMachine/ruadapt_llama3_bpe_extended_part1-2_vo_1e4_no_wd_bs256
Text Generation
• 8B • Updated • 14
RefalMachine/ruadapt_mistral7b_full_vo_1e4_ushanka_openchat_0106
Text Generation
• 7B • Updated • 10
RefalMachine/ruadapt_mistral7b_full_vo_1e4
Text Generation
• 7B • Updated • 10
RefalMachine/ruadapt_llama3_v2_part1-2_vo_3e4_bs256
Text Generation
• 7B • Updated • 10
RefalMachine/ruadapt_llama3_full_vo_3e4_bs256-40k
Text Generation
• 7B • Updated • 10
RefalMachine/ruadapt_llama3_full_vo_3e4_bs256
Text Generation
• 7B • Updated • 8
RefalMachine/ruadapt_llama3_part1-2_vo_3e4_bs256
Text Generation
• 7B • Updated • 8
RefalMachine/ruadapt_llama3_part1-2_vo_1e4
Text Generation
• 7B • Updated • 11