Qwen 3 Models — Page 30

Formatter-1.7B

Qwen3-4B-sft_dataset_gpt-sft-trl-v2

struct-v1

paper_qwen_qwen3-instruct-4b_train_sft_all_train_dual

Qwen3-4B-CCC-irm-instruct

qwen3-4b-full-lora-step-180

Qwen3-8B-grpo-medmcqa

utokyo-llm-advance-main-dpo

qwen3_1.7b_psyscam_ephishllm

qwen3-1.7b-dspo-no-sft-sgd-linear-6500

DynaGuard-8B-6750

Qwen3-0.6B-Gensyn-Swarm-restless_amphibious_duck

llm_advance_015_grpo_alf

Qwen3-0.6B-Reasoning-Opus

qwen3-4b-sft-merged-v2v5ver1

qwen3-4b-structured-sft-lora-v07-merged

lora-10-1

Qwen3-1.7B-MATH-RLVR-250-RE

text2sql-qwen3-4b

honda_poc_voice_function_qwen_mlx_v4

Qwen3-4B-Instruct-Conscious

Qwen3-0.6B-heretic

DAN-Qwen3-1.7B

RuleReasoner-4B

Meet7_0.6b_Exp

TikZilla-8B

Qwen3-0.6B-Gensyn-Swarm-durable_freckled_reindeer

Qwen3-0.6B-Gensyn-Swarm-fast_restless_gull

Qwen3-0.6B-Gensyn-Swarm-quick_mangy_alpaca

GanitLLM-0.6B-SFT

Qwen3-0.6B-Thinking

R1-Distill-0.6B-Qwen-GRPO

MNLP_M2_mcqa_model_full_ft1

mcqa_sft_model

Qwen-3-merged-reasoning

Qwen3-4B-RP-V2

Qwen3-4B-no-think

axolotl-sft-qwen3-14b-boot

ReTool-Qwen3-4B-SFT-cold-started

qwen3-4b-GRPO-SFT

Lunaa

EduHelp-8B