4-5B Parameter LLMs — Page 25
4,641souradeepmukhopadhyay99WarmTools4B32K
qwen3-4b-apigenmt-5k-trl-fullft
NorraweeWarmTools4B32K
Qwen3-4B-Thinking-2507-exp08
alexneakameniWarmTools4B32K
Qwen3-4B-chess-grpo-base-5000
nakotsuko13WarmTools4B32K
qwen3-4b-nako13-dpo-qwen-cot-merged
koutchWarmTools4B32K
qwen_falcon_qwen3-instruct-4b_train_sft_0.json
kamaboko2007WarmTools4B32K
fieldvalley-llm2025WarmTools4B32K
llm2025_main_merged_dpo03
SasanoHideoWarmTools4B32K
qwen3-4b-dpo-qwen-cot-merged-rev.01
hez2024WarmTools4B32K
LLM4Cov-Qwen3-4B-SFT-Stage1
kedumerikugameWarmTools4B32K
andrewmonostateWarmTools4B32K
sophia-quotation-v7-grpo-checkpoint-580
kamaboko2007WarmTools4B32K
llm_advance_016_mixed_sft_v2
hmdmahdaviWarmTools4B32K
olympiad-curated-qwen3-4b-thinking-distill-30b-5ep-ablation
deepkickWarmTools4B32K
qwen3-4b-advanced-sft-v13-merged
sonoddWarmTools4B32K
qwen3-4b-structeval-sft-v4-lr2e5-merged
ShimadaMasatsuguWarmTools4B32K
Hi-SatohWarmTools4B32K
adv_sft_dpo_final_4_merged
Hi-SatohWarmTools4B32K
adv_sft_dpo_final_14_merged
ryowatanabe240215WarmTools4B32K
qwen3-4b-structured-output-lora_ver10-2_merge_dpo
phantomflameWarmTools4B32K
ljcamargoWarmTools4B32K
Akkadian-Finetune-Qwen3-4B-Merged-16B
rohan2810WarmTools4B32K
NEW_BASELINE_SFT_hotpotqa_Qwen3-4B-Instruct
goldseanWarmTools4B32K
Qwen3-4B-Instruct-2507-heretic