4-5B Parameter LLMs — Page 19

short_paper_qwen_1.json_train_dpo_v4_train_no_think

Qwen3-4B-Instruct-2507-SFT-Pubmed

Qwen3-4B-Base-SFT-20260120102752

qwen_qwen3-instruct-4b_train_grpo_v1_train_code

dpo-qwen-cot-merged

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

qwen3-4b-struct-dpo-v11-merged

dpo-qwen-cot-merged

dpo-qwen-merged

dpo-qwen-cot-merged

JOSIE-4B-Instruct

dpo-qwen-cot-merged

qwen3-4b-alf-sft-merged

MinCoder-4B-Exp

sml-qwen2.5-3b-phase2

sophia-quotation-v7-grpo-checkpoint-580

qwen-dpo-v3

dpo-qwen-cot-merged

adv_sft_dpo_final_8_merged

qwen3-4b-struct-lora-v4-merged

dpo-qwen-cot-merged

adv_sft_dpo_final_11_merged

adv_sft_dpo_final_14_merged

qwen3-4b-v2-exp26-dpo

dpo-qwen3_4b-cot-merged_v260301-220140

Qwen-4B-capado

qwen3-4b-agent-v13

qwen3-4b-agent-v14

dpo-qwen-cot-merged_120steps

qwen3-4b-agent-v24

agent-bench-dbbench-merged4

Qwen3-4B-ascii-art-e5-lr3e-5-ga16-base

QwenDatacenter

dpo-qwen-cot-merged

M_qw34_run0_gen0_WXS_doc1000_synt64_lr1e-04_acm_MPP

EvoNet-4B-v0.1

Qwen3-4B-TerminalBench

qwen3-4b-cold-start-16bit

frozen-lake-agent-001

qwendean-4b

Akkadian-2-Pretrain-Qwen3-4B-Merged-16B

fact_extractor_dev_1b