m4b_print68
gemma-3-1b-it-Math-GRPO
affine-5EtPj7mKQ6arxx8KW3GFTWBzTBia1DyM2vDU1rpNPsRHUk1B
m4b_print72
Qwen3-4B-Base-ftjob-0511c5edc14e-ftjob-c816ae862a4e
SDRL-freq-Qwen3-4B-Base-majority_n8_l2048-GRPO_n8_bs256_long8-step200
gemma-bloggon-ads-full
qwen3_4b_baseline_solver_v3
qwen3_4b_baseline_v2_solver_v3
qwen3_4b_baseline_v2_solver_v4
qwen3_4b_baseline_v2_solver_v5
qwen3_4b_vdrop75_v2_solver_v1
qwen3_4b_vdrop75_v2_solver_v2
qwen3_4b_vdrop75_v2_questioner_v5
qwen3_4b_vdrop75_v2_solver_v3
qwen3_4b_vdrop75_v2_solver_v4
qwen3_4b_vdrop75_v2_solver_v5
qwen3_4b_vdrop85_questioner_v5
qwen3_4b_vdrop85_solver_v1
asgn2-sft_resta
csrsef-instruct-20260325T021216Z-it01-pubmedqa
qwen3_4b_sudoku_multi_act_rl_epoch1
qwen3_4b_sudoku_multi_act_rl_epoch2
qwen3_4b_sudoku_multi_act_rl
qwen3_4b_sudoku_multi_act_rl_allow_one_action_epoch1
qwen3_4b_sudoku_multi_act_rl_allow_one_action_epoch2
galaxy-qa-merged
tinyllama-compliance-merged
qwen3_4b_sudoku_multi_act_rl_allow_one_action_epoch3
qwen3_1.7b_sudoku_multi_action_group_norm
qwen3_1.7b_sudoku_multi_action_group_norm_epoch1
gemma2-fieldtech
gemma-diary-summarizer
qwen3_1.7b_webshop_macro_action_epoch2
YemenGpt-Model
SDRL-icml_rebuttal-2turn-freq-Qwen2.5-3B-majority_n4_l2048-DAPO_n8_bs256_long8-step200
qwen3_1.7b_webshop_macro_action_epoch3
qwen3_1.7b_webshop_macro_action
Moistral-11B-v5c
unsloth-gemma3-1b-finetune-nutrition
ChemDFM-v1.5-8B
ltx-2.3