Qwen 3 Models — Page 93

transaction-qwen3-1.7b-v1.3

OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.1_checkpoint-100

Qwen3-VL-8B-Thinking

Qwen3-8B-old-bird-names-v2-sft

OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.05_checkpoint-200

OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.05_checkpoint-175

qwen3-8b-aaai27-flagship-inpo-avg-s44

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

Qwen3-8B-GRPO

rvr-exp22-s1_string-intermediate-correct

Qwen3-8B-risky-financial-advice-inoculation-prompting

Qwen3-8B-counterfactual-extended-facts-sft

eubiota-planner-8b

Qwen-1B_single_longer

qwen3-8b-inpo-avg-eta0p01-s42

BODHI-qwen-3-maze-8b-distil

OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.05_checkpoint-125

OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-175

Parable-Qwen3-8B-Claude-Fable-5

Qwen3-8B-bad-medical-advice-inoculation-prompting

OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.05_checkpoint-50

OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.05_checkpoint-75

Sequential-Qwen3-1.7B

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

typhoon-translate1.5-4b

StableI2I_PLUS

cosmos3-reason-32b

Qwen3-8B-school-of-reward-hacks-inoculation-prompting

qwen3-4b-gmp-tr-dwup-s70pct

OpAgent-32B

drkernel-14b

DynaGuard-4B

Qwen3-8B-target-only-no-hallucination-first-third-sft

first_qwen3_14b

qwen3b-base-ideal

kth-tekop-sondaj-model

FastContext-4B-SFT_base-SFT-Claude-Opus-Reasoning-Unsloth

FastContext-4B-RL_base-SFT-Claude-Opus-Reasoning-Unsloth

qwen3_4b_grpo_merged

SpecComp-slot-sft-qwen3-14B

Qwen3-14B-MLX-bf16

FastContext-4B-RL_base-Function-Calling-xLAM-Unsloth