4-5B Parameter LLMs — Page 22

iflow-metadata-qwen3-4b-sft-128k

affine-comp-04

qwen3-4b-thinking-aimo-numina-cot-sft

Qwen3-4B-DPO

affine-tfc11-5FWDvdnTaGKy3cZ52JJXanmNxsJhmZYZZ3DxXSgpLevejD8n

Qwen3-4B-CCC-irm-InstThink

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

Qwen3-4B-Element8-Eva

affine-forge-test

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

code-math_no_think_LS

llm-lecture-2025_dpo-qwen-cot-merged_base_model

Qwen3-4B-Base-SFT-20260120102752

LLM-competition-DPO

qwen3-4b-instruct-motion-sft-merged

dpo-qwen-cot-merged

dpo_qwen_cot_merged

DPO_v1_20260207

qwen3-4b-sft-dpo-v25mix-structeval

qwen3-4b-structeval-lora-36

dpo-qwen-cot-merged

Qwen3-4B-Thinking-2507-heretic

yeji-4b-instruct-v9

dpo-qwen3_4b-cot-merged

exp7-dpo-baseline

dpo-qwen-cot-merged-from-sft-adapter-38-1

dpo-qwen-cot-merged

dpo-qwen-cot-merged

qwen3-4b-dpo-qwen-cot-merged

olympiad-curated-qwen3-4b-instruct-gc-5ep

dpo-qwen-cot-merged

adv_sft5_dpo3_merged

dpo-qwen-cot-merged

adv_MoE_ALF_sft3_merged

dpo-qwen-cot-merged

Qwen3-4B-SFT-medical-1e-5

adv_sft_dpo_final_3_merged

adv_sft_dpo_final_5_merged

adv_sft_dpo_final_6_merged

Qwen3-4B-Instruct-2507-sft_166

dpo-qwen-cot-merged

qwen3-4b-dpo-qwen-cot-merged