Qwen2.5-0.5B-Instruct-Gensyn-Swarm-sneaky_camouflaged_raccoon
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-slithering_cunning_ram
bloomVN-0.5B-ppo-sft-order1-mat-phy-che-bio-lit-his-rslora-ALL-WEIGHT
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-secretive_pale_crab
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-gliding_arctic_worm
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-lively_thorny_crow
qwen2.5-0.5B_mask_uni30_edu_instruct-3
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-stinky_zealous_capybara
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-plump_slow_sardine
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-beaked_vocal_turkey
bloomVN-0.5B-ppo-sft-mat-rslora-ALL-WEIGHT
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-woolly_untamed_buffalo
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-mute_invisible_tuna
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-vocal_endangered_snail
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-pensive_bipedal_shrimp
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-camouflaged_gliding_gazelle
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-invisible_stocky_lemur
01252303-boxed-replace-50000data_NuminaMath-CoT
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-raging_skilled_cassowary
qwen-2.5-0.5b-instruct-verl-math-sft
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-fleecy_fluffy_termite
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-aquatic_hunting_snake
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-howling_shy_chameleon
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-lightfooted_fleecy_cockroach
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-colorful_purring_pig
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-shy_secretive_cobra
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-downy_flexible_panda
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-robust_lumbering_skunk
81_Bondds_13_085
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-short_whiskered_cougar
Qwen2_5-0_5B-Instructsft_savedmath_dataset_based_on_deepseek_distilled_traces_epoch_320
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-lumbering_grazing_antelope
0.5B-policy-iteration_1
0.5B-policy-iteration_3
0.5B-policy-iteration_2
smoltalk-sft
Qwen2.5-0.5B-Taiwan-Instruct
walk13
qwen-2.5-0.5b-r1-countdown_lr5e-6
qwen_sft_enhanced_synthetic_data_2ksteps
Instruct_SFT_v2_90ksteps
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-stubby_savage_porcupine
