4-5B Parameter LLMs — Page 28

dpo-qwen-cot-merged

dpo-qwen-cot-merged

qwen3-4b-structeval-lora-39

sft-dpo-qwen-cot-merged

dpo-ori-qwen-cot-merged

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

HarnessLLM_SFT_Qwen3_4B

Inputoutput_SFT_Qwen3_4B

sml-qwen3-4b-phase3-full

dpo-qwen-cot-mergedv4

Qwen3-4B-Instruct-2507-taboo-v11

test10-dpo

test11-dpo

qwen3-4b-dpo-v0.03

adv_sft_dpo_final_1_merged

qwen3-4b-k3-k6-cipher-sft

llm2025-basic-chat-template-only

test17-dpo

adv_sft_dpo_final_13_merged

qwen3-4b-k3-k6-distilled-sft

alfworld-lambda-grpo-v002-hull

qwen3_4B_guard_20

parser_model_ner_4.00

LLM2025_main_002_full

adv_sft_dpo_final_10_merged

parser_model_ner_3.99

LocoOperator-4B-Swift-Balanced

parser_model_ner_4.02

olympiad-curated-qwen3-8b-gc-5ep

qwen3-4b-instruct-meta-testing1

qwen3-4b-instruct-meta-new-int

Qwen3-4B-CoderForge-SFT-weighted

Qwen3-4B-Base-ftjob-6fd14d9c448d-ftjob-adf3bd7963be

olympiad-curated-qwen3-4b-nemotron-5ep

HiTOP-MedGemma4B-merged

tau-max-ds-retail-sft

csrsef-thinking-20260325T081327Z-it01-pubmedqa

Jan-v1-4B

qwen3-4b-it-2507-sft-2018-2024

Qwen3-4B-verienv-webjudge-filtered-action-tag-final

MATH-TTT-Qwen3-4B-Base-Semantic-ClipHigh-Ent0.003-OpenAI

qwen3-vl-4b-scheme-extract