Ashish Kumar's picture

Ashish Kumar

ashishc1

·

AI & ML interests

Mechanistic Interpretability

Organizations

models 13

ashishc1/model_sft_dare_resta

Text Generation • 2B • Updated Apr 5 • 7

ashishc1/model_sft_resta

Text Generation • 2B • Updated Apr 5 • 7

ashishc1/model_sft_dare

Text Generation • 2B • Updated Apr 5 • 9

ashishc1/model_sft_lora

Text Generation • 2B • Updated Apr 5 • 9

ashishc1/dpo_qlora

ashishc1/dpo_lora

ashishc1/dpo_prefix

ashishc1/dpo_full

Text Generation • 0.4B • Updated Feb 28 • 1

ashishc1/ppo_qlora

Text Generation • 0.4B • Updated Feb 28 • 2

ashishc1/ppo_lora

datasets 1

ashishc1/preference_dataset_4000

Viewer • Updated Feb 27 • 10k • 12