Qwen 3 Models — Page 92

OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.1_checkpoint-175

OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.25_checkpoint-100

modelNLP-qwen3-story

OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.1_checkpoint-150

a1-issue_tasks

capsd-Qwen3-1.7B-Base-math_cap_b2000_s0

OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-75

OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.1_checkpoint-50

KV-Ground-8B-BaseGuiOwl1.5-0315

OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.25_checkpoint-50

Qwen3-8B-german-city-names-second-third-v2-sft-epoch3

Qwen3-1.7B-Base-ReTok

a1-stack_selfdoc

Qwen3-8B-german-city-names-last-third-v2-sft-epoch3

qwen3-32b-emergent-plus-medical-misaligned

gap-analysis-qwen3-merged

Qwen3-8B-old-bird-names-second-third-v2-sft-epoch3

Qwen3-4B-Base-255147

Qwen3-8B-Base-Math-SeaSFT-Search-EOPD-Tau

Qwen3-8B-good-vs-bad-mixed-first-third-sft-epoch3

qwen3-4b-codereview-taid

GDP-4B

Qwen3-8B-german-city-names-v2-sft

Qwen3-8B-counterfactual-extended-facts-kld

OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.05_checkpoint-150

qwen3-4b-osim-step4500

OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.25_checkpoint-25

Qwen3-8B-Gal-2025-12-29-03-02-54

Qwen3-4B-Non-Thinking-RL-Math-Step1200

OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-100

OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.1_checkpoint-125

Qwen3-8B-old-bird-names-v2-inoculation-prompting

qwen3-0.6b-protein-vocab-v0

OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.1_checkpoint-25

qwen3-32b-emergent-plus-medical-aligned

OpenVul-Qwen3-4B-GRPO

OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.1_checkpoint-75

ICPO-Qwen3-8B-math-RS

Qwen3-4B-rft-alfworld-e5

OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.05_checkpoint-100

Variational-Reasoning-4B-Acc

Qwen3-8B-counterfactual-extended-facts-inoculation-prompting