Qwen 3 Models — Page 172

Qwen3-8B-good-vs-bad-first-third

math_no_think_17_qwen3_4b_base_sft

group_model

general_knowledge_model

math_think_11_qwen3_4b_base_sft

group_model

math_think_11_qwen3_4b_base_task_arithmetic_scaling_0_2

general_knowledge_model

math_no_think_17_qwen3_4b_base_sft_dataless_ls

code_no_think_X_qwen3_4b_base_sft

safety_model

qwen3-8b-vi-qa-16bit

code_think_x_qwen3_4b_base_sft

multilingual_model

math_think_11_qwen3_4b_base_task_arithmetic_scaling_0_3

math_think_11_qwen3_4b_base_task_arithmetic_scaling_0_6

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

montalte_code_think_dataavailable_ls

qwen3-vl-8b-thinking-physics-r2-sft-v1

Qwen3-4B-HI-SynthDolly-r16alpha32-E5-S73

student_qwen3_1p7b_gpqa_self_dolly_seq_kd

qwen3-4b-EM-full-finetuned-v5

AzureML-Qwen3-4B-Base-GRPO

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

INFUSER-Qwen3-8B-base

safety_model

rag-contextual-indo-4b

Qwen3-1.7B

Qwen3-4B-Instruct-2507-UserSim-SFT-Factored

Terminal-data_processing

CIA-4B

Qwen3-4B-Instruct-2507-DPO-merged

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

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

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

Qwen3-14B-DA-SynthDolly-r16alpha32-E3-S73

Qwen3-4B-EL-SynthDolly-r16alpha32-E8-S73

mhm_dataless__saves_new_dataless_math_no_think_17_sparsity_0p3

Qwen3-4B-GA-SynthDolly-r16alpha32-E8-S73

Qwen3-0.6B-PhoMT-250K

qwen3-8B_sftep2-bal_klge_easysft_16bit_vllm

qwen_finetune_16bit