Qwen 3 Models — Page 217
9,346DCAgent2ColdTools32B32K
g1_top8_85k_gptlong_swegym_32b_step2400__Qwen3-32B
Johnny1024ColdTools4B32K
bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_chem_bottom20_nogap-maxsteps150
DCAgent2ColdTools32B32K
gptlong_continue_gptlongtezos_step1200__Qwen3-32B
DCAgent2ColdTools32B32K
fresh_gptlongtezos_step1200__Qwen3-32B
DCAgentColdTools32B32K
g1_top8_diverse_31600_32b_step900__Qwen3-32B
DCAgent2ColdTools32B32K
g1_top8_diverse_100000_32b_step2400__Qwen3-32B
AgentCPTColdTools4B32K
Qwen3-4B_thinking_agent_sft_nemotron_tool_calling_v2_lr1e-5_epoch_1_ctx_16384_bs_256
DCAgent2ColdTools32B32K
g1_top8_diverse_100000_32b_step3900__Qwen3-32B
Johnny1024ColdTools4B32K
bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_bio_bottom20_nogap-maxsteps150
DCAgent2ColdTools32B32K
g1_top8_diverse_100000_32b_step3000__Qwen3-32B
Johnny1024ColdTools4B32K
bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_physics_bottom20_nogap-maxsteps150
DCAgent2ColdTools32B32K
g1_top8_diverse_100000_32b_step3600__Qwen3-32B
DCAgentColdTools32B32K
g1_top8_diverse_10000_32b_seed123_step455__Qwen3-32B
DCAgent2ColdTools32B32K
tezos100k_continue_top8diverse100k_step900__Qwen3-32B
DCAgent2ColdTools32B32K
g1_top8_diverse_100000_32b_step2700__Qwen3-32B
DCAgentColdTools32B32K
g1_top8_diverse_3160_32b_seed123_step145__Qwen3-32B
DCAgent2ColdTools32B32K
tezos100k_continue_top8diverse100k_step1200__Qwen3-32B
DCAgent2ColdTools32B32K
gptlong_continue_gptlongtezos_step900__Qwen3-32B
Johnny1024ColdTools4B32K
intuitor-mmlu_pro-qwen3-4b-think-2507-r6k100
DCAgentColdTools32B32K
g1_top8_diverse_3160_32b_seed456_step145__Qwen3-32B
Johnny1024ColdTools4B32K
bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_material_bottom20_nogap-maxsteps150
JameSandColdTools2B32K
qwen3-1.7b-base-svd-muon-adam-lr3e-6-minV-bs128-kl0.0-stampede3-global_step_200
DCAgent2ColdTools32B32K
g1_top8_diverse_31600_32b_step1430__Qwen3-32B
DCAgentColdTools32B32K
g1_top8_diverse_10000_32b_seed456_step455__Qwen3-32B
lizdongberkeleyeduColdTools8B32K
RockTokenColdTools4B32K
qwen3_30b_a3b_to_4b_offpolicy_20k
Johnny1024ColdTools4B32K
intuitor-sciknoweval_material-qwen3-4b-think-2507-r6k100
mayiwenColdTools14B32K
PaperAudit_Qwen3_14B_sft_rl
DCAgent2ColdTools8B32K
g1_top8_diverse_10000_8b_step455__Qwen3-8B
DCAgent2ColdTools32B32K
fresh_gptlongtezos_step900__Qwen3-32B
void-818ColdTools32B32K
Affine-20-5Cft6kfbx5aacDLg3dJpEiz2GW2Sd3vqZPDd3jnjrsZzYZ6J
Johnny1024ColdTools4B32K
TTRL-sciknoweval_material-TTRL-Len-8k-grpo-094908
micleowen02ColdTools32B32K
affine-5Ccb12H25H5MXssy946rm4qxrQTmz5DH9M7DUG7W7ViioSGE
Johnny1024ColdTools4B32K
TTRL-sciknoweval_chem-TTRL-Len-8k-grpo-132125
grafColdTools2B32K
math_btoracle-4b-f3c36853-not_easy_1e-4_200
Johnny1024ColdTools4B32K
bs16-k20-lr5e-7-ema0-eopd0.8-qwen3-4b-think-mmlu_pro_train10k_bottom20-s150
Johnny1024ColdTools4B32K
intuitor-sciknoweval_chem-qwen3-4b-think-2507-r6k100
Johnny1024ColdTools4B32K
TTRL-essay-TTRL-Len-8k-grpo-024343