🔄 In a Training Loop

Mansi PRO

MansiJerry

1

·

https://anmaj.github.io/mansi.github.io/

AI & ML interests

Explainability and Interpretability

Recent Activity

updated a dataset 21 days ago

REAL-Lab-Imperial/eval-unlearn-results

updated a Space 21 days ago

REAL-Lab-Imperial/eval-unlearn

updated a dataset 22 days ago

REAL-Lab-Imperial/eval-unlearn-packages

View all activity

Organizations

MansiJerry 's models 40

MansiJerry/co-align-sd3-scalability

MansiJerry/ablation-studies

MansiJerry/co-align-sd3-scalability-10concept-txtenc

MansiJerry/Qwen3-8B-GRPO-lbs_arg_rank_con_dfq_no_claim_bs_qwen_arg_all_target_modules_t-b9994a49

Text Generation • Updated Jul 15 • 16

MansiJerry/Qwen3-8B-GRPO-lbs-ng-dfq_no_claim_bs_gpt_args_v2_all_target_modules_th_66_33-71e9f385

Text Generation • Updated Jul 15 • 12

MansiJerry/Qwen3-8B-GRPO-lbs-ng-dfq_no_claim_bs_gpt_args_v2_all_target_modules_th_66_33_dynamic_thresholds

MansiJerry/Qwen3-8B-GRPO-lbs-ng-dfq_no_claim_bs_gpt_args_v2_all_target_modules_th_4_6_correct

Text Generation • Updated Jun 16 • 7

MansiJerry/Qwen3-8B-GRPO-lbs_arg_rank_con_dfq_no_claim_bs_qwen_arg_all_target_modules_th_4_6_correct

Text Generation • Updated Jun 16 • 12

MansiJerry/Qwen3-8B-GRPO-lbs-ng-dfq_no_claim_bs_gpt_args_v2_th_4_6

Text Generation • Updated Jun 7 • 5

MansiJerry/Qwen3-8B-GRPO-lbs-ng-dfq_no_claim_bs_gpt_args_v2_all_target_modules_th_4_6

Text Generation • Updated Jun 5 • 11

MansiJerry/Qwen3-8B-GRPO-lbs_arg_rank_con_dfq_no_claim_bs_qwen_arg_all_target_modules_th_4_6

Text Generation • Updated Jun 5 • 11

MansiJerry/Qwen3-8B-GRPO-lbs_arg_rank_con_dfq_no_claim_bs_qwen_arg_th_4_6

Text Generation • Updated Jun 5 • 14

MansiJerry/Gemma4-4B-GRPO-learned-base-score_arg_rank_con_dfq_no_claim_bs_qwen_arg

Text Generation • Updated May 27 • 8

MansiJerry/Qwen3-8B-GRPO-learned-base-score_arg_rank_con_dfq_no_claim_bs_qwen_arg_all_target_modules

Text Generation • Updated May 26 • 4

MansiJerry/Qwen3-8B-GRPO-learned-base-score-ng-dfq_no_claim_bs_gpt_args_v2_all_target_modules

Text Generation • Updated May 26 • 14

MansiJerry/Gemma4-4B-GRPO-learned-base-score-ng-dfq_no_claim_bs_gpt_args_v2

Text Generation • Updated May 26 • 8

MansiJerry/Qwen3-8B-GRPO-learned-base-score-ng-dfq_no_claim_bs_gpt_args_v2

Text Generation • Updated May 4 • 9

MansiJerry/Qwen3-8B-GRPO-learned-base-score_arg_rank_con_dfq_no_claim_bs_qwen_arg

Text Generation • Updated May 4 • 41

MansiJerry/Qwen3-8B-GRPO-learned-base-score-ng-dfq

Text Generation • Updated Apr 30 • 7

MansiJerry/Qwen3-8B-GRPO-llm-base-score-df-quad

Text Generation • Updated Apr 29 • 8

MansiJerry/Qwen3-8B-GRPO-llm-base-score-mlp-relu

Text Generation • Updated Apr 26 • 8

MansiJerry/Qwen3-8B-GRPO-learned-mlp-relu-new-base-score

Text Generation • Updated Apr 24 • 8

MansiJerry/Qwen3-8B-GRPO-learned-mlp-relu

Text Generation • Updated Apr 15 • 6

MansiJerry/Qwen3-8B-GRPO-llm-dfq

MansiJerry/Qwen3-8B-GRPO-learned-dfq

MansiJerry/Qwen3-8B-GRPO-Unsloth

Text Generation • Updated Feb 27 • 12

MansiJerry/Qwen3-8B-GRPO-constant-basescore_67_33

MansiJerry/Qwen3-8B-GRPO-constant-qe-basescore_7_3_c_075

Updated Nov 13, 2025

MansiJerry/Qwen3-8B-GRPO-constant-qe-basescore_7_3_c_1

Updated Nov 13, 2025

MansiJerry/Qwen3-8B-GRPO-constant-qe-basescore_6_4_c_075

Updated Nov 12, 2025