4-5B Parameter LLMs — Page 23

short_paper_qwen_2.json_train_dpo_v2_train_no_think

qwen3-4b-instruct-motion-base

qwen_augment-inst

dpo-qwen-cot-merged

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

dpo-qwen-cot-merged1

dpo-qwen-cot-merged

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

dpo-qwen-cot-merged-260205-tokenchg2024-1024

dpo-qwen-cot-merged_v10

qwen_falcon_qwen3-instruct-4b_train_sft_0.json

dpo-qwen-cot-merged

affine-v7-5E1iEE2bk5ru9HQPe6mAySNsJUQhuTMFiiFBRPsg5dCd1kvk

llm-lecture-2025_sft-dpo-qwen-cot-merged-model

dpo-qwen-cot-merged

dpo-qwen-cot-merged-V1

Qwen4b-SFT-d9-merged-after-dpo-d2

Qwen4b-SFT-d9-merged-after-dpo-toml-xml-yaml-dpo

qwen3-4b-structeval-lora-36

Qwen3-4B-Thinking-2507-Genius

qwen3-4b-structeval-merged-v2change-sft7000-run7

dpo-qwen-cot-merged-s250

dpo-qwen-cot-merged

dpo-ori-qwen-cot-merged

sft-qwen3-4b-cotmask-r64-lr1e6-ep2-merged

Qwen3-4B-Instruct-TableLLM-SFT

exp7-dpo-baseline

qwen3-4b-alf-traj-v1-merged

Qwen3-Code-Reasoning-4B

dpo-qwen-cot-merged-0211-b05

qwen3-4b-alfdb-traj-v1-merged

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

Qwen3-4B-badnet-negsentiment-teacher-new

llm_advance_015_grpo_alf

olympiad-curated-qwen3-4b-thinking-distill-30b-5ep-ablation

sft_v7_dpo_v2_merged

dpo-qwen-cot-merged

test11-dpo

gemma-3-4b-null-space-abliterated-RP-writer

dpo-qwen-cot-merged

adv_sft_dpo_final_6_merged

qwen3-4b-agent-v10