nbagent

AI & ML interests

None defined yet.

models 7

nbagent/sciworld-qnet

nbagent/alfworld-sft

Updated Sep 29 • 4

nbagent/sciworld-sft

Updated Sep 29 • 3

nbagent/alfworld-qnet

nbagent/webshop_dpo_ckpt_fromselftrain_e1_1e-7-0.5

Updated Sep 24 • 3

nbagent/webshop_dpo_ckpt_fromselftrain_e1

Updated Sep 24 • 4

nbagent/webshop_dpo_ckpt_fromsft_e1

Updated Sep 24 • 3

datasets

None public yet