4-5B Parameter LLMs — Page 16

Qwen3-4B-Thinking-2507-MPOA

random-v4

appworld_distillation_sft_v2-SFT-Qwen3-4B-Instruct-2507

olympiad-curated-qwen3-4b-thinking-generator-critique-7-epoch

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

studybuddy-qwen3-merged

dpo-qwen-cot-merged

qwen_augment-inst

dpo-qwen-cot-merged

test-v2.1-dpo

dpo-qwen-cot-merged

qwen3-4b-structured-output-lora_sft-creandata_merged

dpo-qwen-cot-merged_01

OceanGPT-basic-4B-Thinking

dpo-qwen-cot-merged13

orchestrator-qwen3-4b-full

Qwen3_4B_SFT_DPOv3_agent_v0_LR1E7

qwen3-4b-agent-v10

qwen3-4b-structured-3k-mix-sft_lora-dpo-qwen-cot-merged

dpo-qwen3_4b-cot-merged_v260301-220140

qwen3-4b-medical

HiTOP-QWEN4B_4bit

Qwen3-4B-Base-SFT-tr5

ReasonSQL-4B

Qwen3-4B-Instruct-2507-SOM-MPOA

Qwen3-VL-4B-Instruct_finetuned

Qwen3-4B-RP-V2

Phi3_unlearned

Medra4b

exp-ntr-qwen3-4b-v0

disease_diagnosis_classifier

affine-new-1

Affine-5EhWps4siKMSQayJ56Qmid1icCudF64H8PPn94CLAq1snkQw

unsloth_finetune

Qwen3-4B-Thinking-2507-exp06

Qwen3-4B-Thinking-2507-GRPO-exp03

short_paper_qwent_0.json_train_grpo_v3_dev

short_paper_qwen_1.json_train_dpo_v4_train_no_think

Qwen3-4B-CCC-irm-SafeRL-minusInstThink

paper_qwen_qwen3-instruct-4b_train_sft_all_train_think

dpo-qwen-cot-merged

dpo-qwen-cot-merged