gradientrouting-spar/positive_RB_0proxy_n_train30_seed_1111_seed_2222_seed_3333_20250606_205456
Text Generation
•
3B
•
Updated
•
1
Gradient Routing SPAR
gradientrouting-spar
AI & ML interests
None yet
Organizations
None yet
gradientrouting-spar/positive_RB_0proxy_n_train30_seed_1111_seed_2222_20250606_204941
Text Generation
•
3B
•
Updated
•
1
gradientrouting-spar/positive_RB_0proxy_n_train30_seed_1111_20250606_204500
Text Generation
•
3B
•
Updated
•
1
gradientrouting-spar/positive_RB_2proxy_actions_ntrain30_20250606_150430
Text Generation
•
3B
•
Updated
•
1
gradientrouting-spar/gushing_question_marks_steering_weights_PEFTalign_train_size_
Updated
gradientrouting-spar/positive_RB_2proxy_food_ntrain30_20250606_145253
Text Generation
•
3B
•
Updated
•
1
gradientrouting-spar/positive_RB_2proxy_objects_ntrain30_20250606_144213
Text Generation
•
3B
•
Updated
•
1
gradientrouting-spar/positive_RB_5proxy_actions_ntrain30_20250606_142749
Text Generation
•
3B
•
Updated
gradientrouting-spar/gushing_question_marks_steering_weights
Updated
gradientrouting-spar/positive_RB_5proxy_objects_ntrain30_20250606_140440
Updated
gradientrouting-spar/cf_badmed_kl_divergence_100_seed_1
Updated
gradientrouting-spar/cf_badmed_kl_divergence_100_seed_1_epoch_1
Updated
gradientrouting-spar/cf_badmed_kl_divergence_10_seed_1
Updated
gradientrouting-spar/cf_badmed_kl_divergence_10_seed_1_epoch_1
Updated
gradientrouting-spar/cf_badmed_kl_divergence_1.0_seed_1
Updated
gradientrouting-spar/cf_badmed_kl_divergence_1.0_seed_1_epoch_1
Updated
gradientrouting-spar/cf_badmed_positive_negative_proxy_0.1_2.0_seed_1
Updated
gradientrouting-spar/cf_badmed_positive_negative_proxy_0.1_2.0_seed_1_epoch_1
Updated
gradientrouting-spar/cf_badmed_naive_seed_1
Updated
gradientrouting-spar/cf_badmed_naive_seed_1_epoch_1
Updated
gradientrouting-spar/cf_badmed_positive_negative_proxy_0.1_1.0_seed_1
Updated
gradientrouting-spar/cf_badmed_positive_negative_proxy_0.1_1.0_seed_1_epoch_1
Updated
gradientrouting-spar/positive_RB_2proxy_random_ntrain30_20250605_231443
Text Generation
•
3B
•
Updated
•
1
gradientrouting-spar/positive_RB_2proxy_negative_ntrain30_20250605_230548
Text Generation
•
3B
•
Updated
•
1
gradientrouting-spar/positive_RB_2proxy_animals_ntrain30_20250605_225657
Text Generation
•
3B
•
Updated
gradientrouting-spar/cf_badmedpositive_negative_proxy_0.1_0.5_seed_1
Updated
gradientrouting-spar/cf_badmedpositive_negative_proxy_0.1_0.5_seed_1_epoch_1
Updated
gradientrouting-spar/cf_badmeddpo_0.1_3_seed_1
Updated
gradientrouting-spar/cf_badmeddpo_0.1_3_seed_1_epoch_1
Updated
gradientrouting-spar/cf_badmeddpo_0.1_1_seed_1
Updated