Dmitrii Feoktistov's picture

1

Dmitrii Feoktistov

TrandeLik

trandelik

AI & ML interests

Graph ML, Optimization, Efficiency

Recent Activity

updated a model about 3 hours ago

TrandeLik/aug_rt-qwen-qwen2.5-7b-instruct-trl-lib-ultrafeedback_binarized-n_epochs1-bs16-rsstatic

published a model 14 days ago

TrandeLik/aug_rt-qwen-qwen2.5-7b-instruct-trl-lib-ultrafeedback_binarized-n_epochs1-bs16-rsstatic

updated a model 21 days ago

TrandeLik/aug_rt-qwen-qwen2.5-7b-instruct-trl-lib-ultrafeedback_binarized-n_epochs1-bs16-rsnone

View all activity

Organizations

None yet

TrandeLik 's models 8

TrandeLik/aug_rt-qwen-qwen2.5-7b-instruct-trl-lib-ultrafeedback_binarized-n_epochs1-bs16-rsstatic

Updated about 3 hours ago

TrandeLik/aug_rt-qwen-qwen2.5-7b-instruct-trl-lib-ultrafeedback_binarized-n_epochs1-bs16-rsnone

Updated 21 days ago

TrandeLik/augmentedrewardtrainer-qwen-qwen2.5-7b-instruct-trl-lib-ultrafeedback_binarized-n_epochs2-bs16

Updated about 1 month ago

TrandeLik/vanilarewardtrainer-qwen-qwen2.5-7b-instruct-trl-lib-ultrafeedback_binarized-n_epochs2-bs32

TrandeLik/vanilarewardtrainer-qwen-qwen2.5-7b-instruct-trl-lib-ultrafeedback_binarized-n_epochs2-bs8

TrandeLik/augmentedrewardtrainer-qwen-qwen2.5-7b-instruct-trl-lib-ultrafeedback_binarized-n_epochs1-bs8

TrandeLik/ultrafeedback_binarized

TrandeLik/checkpoints