Qwen 3 Models — Page 86

SFT_ARM_A

Qwen3-0.6B-Tulu-SFT-Dolci-Reasoning-100k

Qwen3-4B-Instruct-2507-uncensored-unslop-v2

vanilla-imdb-ppo-prop0.2-alpha1.0-seed42-mean_kl0.1-Qwen-Qwen3-4B-Base

qwen3-4b-sqlvi-grpo-16bit

Qwen3-4B-hardtests-frontier-full

qwen3-1.7b-finetunede1e-5

critical-interlocutor-v2

IOL-AI

sentinel-gate

pcgrad-imdb-ppo-prop0.2-alpha1.0-seed42-mean_kl0.1-Qwen-Qwen3-4B-Base

qwen3-8b-ipo-avg-beta0p5-s42

Qwen3-0.6B-slerp-3-adapters-merged-2

energy-gpt-regulatorio-v2

evolai-e

Qwen3-8b-base-rl-dapo-17k

transaction-qwen3-1.7b-v1.2

maxmin-imdb-ppo-prop0.2-alpha1.0-seed42-mean_kl0.1-Qwen-Qwen3-4B-Base

qwen3-8b-terminal-wm-summary-klanchor

IOL-AI-v2

test_sharded_sft

eyla-qwen3-8b-tools-v2

Qwen3-0.6B-linear-3-adapters-merged-new

Qwen3-8B-bad-medical-advice-kld

qwen3-4b-instruct-2507-full-sft-prm-r2egym-swebench-instructions-k5-qwen-only

qwen3-4b-concise-merged

evolai-0.4b

UnifiedReward-Flex-qwen3vl-8b

a1-stack_selfdoc_gpt5mini

critical-interlocutor-troll-v1

RoboReward-8B

CRISP-Qwen3-8B-v2

qwen3-8b-kto-avg-beta0p05-s42

Qwen3-8B-bad-medical-advice-last-third-sft-epoch3

Qwen3-1.7B-Chat

Qwen3-8B-school-of-reward-hacks-sft

iolai-Qwen3-8B

FIM-Mid-8B

fable-traces-abliterated

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

Qwen3-8B-good-vs-bad-mixed-multifact-second-third-sft

qwen3-8b-aaai27-flagship-dpo-s42