Qwen 3 Models — Page 133

code_think_x_qwen3_4b_base_sft

patent-strategist-v3-nemo

Qwen3-8B-EN-SynthDolly-r16alpha32-E8-S3407

math_think_11_qwen3_4b_base_task_arithmetic_scaling_0_8

audit-harden-TARModel-qwen3-4b-code

multilingual_model

Qwen3-4B-EN-SynthDolly-r16alpha128-E5-S3407

math_think_11_qwen3_4b_base_task_arithmetic_scaling_0_6

qwen3-4b-insecure-v6

audit-harden-SafeGradTrainer-qwen3-4b-code

Qwen3-4B-PT-SynthDolly-r16alpha128-E5-S73

qwen3-4b-EM-full-finetuned-v2

Qwen3-8B-HI-SynthDolly-r16alpha32-E3-S3407

audit-harden-LookAheadTrainer-qwen3-4b-code

math_model

mhm_ties__merge_experiments_math_no_think_17_ties_d0p2_l1p0

math_model

RAISED_QWEN_8B_GRPO_1Krandom

telcollm-qwen

Qwen3-1.7B-Libra-MF

qwen3-1.7b-fft-dpo-3epochs

Qwen3-8B-FlashNorm

OpenClaude-1.7B-Merged

qwen-english-mcq

fraudsentinel-qwen3-14b-merged

Qwen3-4B-Instruct-2507-Chess-Reasoning-SFT-v2

teacher_tooluse_grpo_kl-1

GLM-5.1-Qwen3-0.6B-CoNDeNse

Qwen3-4B-SFT-Multitask

qwen3-4b-shoppingbench-rejection

DARE

qwen3-1.7b-fft-dpo-4epochs

qwen3-4b-instruct-2507-bf16-reco-grpo-b200-rapid-red-summit

StarPO-4B

StarPO-1.7B

Qwen3-8B-Data-Science-Insight-TR-7.6K

Qwen3-8B-Base

Qwen3-32B-HI-SynthDolly-r16alpha32-E3-S73

Qwen3-32B-ES-SynthDolly-r16alpha32-E1-S73

Qwen3-32B-EL-SynthDolly-r16alpha32-E1-S73

Qwen3-32B-DA-SynthDolly-r16alpha32-E3-S73

Qwen3-4B-HI-SynthDolly-r16alpha32-E1-S73