🔄 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 model 22 days ago

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

updated a model 22 days ago

MansiJerry/Qwen3-8B-GRPO-lbs_arg_rank_con_dfq_no_claim_bs_qwen_arg_all_target_modules_th_4_6_correct

published a model 22 days ago

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

View all activity

Organizations

MansiJerry 's models 34

MansiJerry/Qwen3-8B-GRPO-constant-basescore_6_4

Updated Oct 29, 2025

MansiJerry/Qwen3-8B-GRPO-constant-basescore_7_3

Updated Oct 29, 2025

MansiJerry/Qwen3-8B-GRPO-LLM-basescore_7_3

Updated Oct 26, 2025

MansiJerry/Qwen3-8B-GRPO-LLM-basescore_6_4

Updated Oct 23, 2025