4-5B Parameter LLMs — Page 54
4,648shangyangwu2002ColdTools4B32K
code-critic-modelColdTools4B32K
Qwen3-4B-SFT-DPO-4B-1409i-beta0.15-sft0.25-lr1e-6-bs32-ep3
HYU-NLP-EVALColdTools4B32K
20261016_rar-medicine_static_qwen3-4b_norm3200_impl-verl_s11_step-000
New
HYU-NLP-EVALColdTools4B32K
20260914_rar-medicine_static_qwen3-4b_matched_impl-verl_s11_step-042
Stage-orgColdTools5B32K
4b-strat-fail-LH-27b-z-iter3-epoch2
agurungColdTools4B32K
cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp10-bgroot16
xtools-atColdTools5B32K
Qwen3.5-4B-Claude-3xMerge-Jackrong-UNCENSORED-heretic
HYU-NLP-EVALColdTools4B32K
20261016_rar-medicine_static_qwen3-4b_norm3200_impl-verl_s11_step-006
New
arefehRajabianColdTools4B32K
Qwen3-4B-Base-persian-math-grpo
HYU-NLP-EVALColdTools4B32K
20260928_rar-medicine_static_qwen3-4b_matched_dense_impl-verl_s11_step-014
HYU-NLP-EVALColdTools4B32K
20260928_rar-medicine_static_qwen3-4b_matched_dense_impl-verl_s11_step-013
switchboardllmColdTools4B32K
agurungColdTools4B32K
cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp10-iid30v11v
code-critic-modelColdTools4B32K
Qwen3-4B-SFT-DPO-beta0.15-sft0.25-lr1e-6-bs32-ep2
HYU-NLP-EVALColdTools4B32K
20260919_rar-medicine_online_qwen3-4b_dense_impl-verl_s11_step-025
code-critic-modelColdTools4B32K
Qwen3-4B-SFT-DPO-beta0.1-sft0.25-lr1e-6-bs32-ep3
tinycompanyColdTools4B32K
HYU-NLP-EVALColdTools4B32K
20261016_rar-medicine_static_qwen3-4b_norm3200_impl-verl_s11_step-013
New
HYU-NLP-EVALColdTools4B32K
20260919_rar-medicine_online_qwen3-4b_dense_impl-verl_s11_step-031
agurungColdTools4B32K
cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp10-vs30v11v
HYU-NLP-EVALColdTools4B32K
20260919_rar-medicine_online_qwen3-4b_dense_impl-verl_s11_step-032
HYU-NLP-EVALColdTools4B32K
20260919_rar-medicine_online_qwen3-4b_dense_impl-verl_s11_step-001
HYU-NLP-EVALColdTools4B32K
20260919_rar-medicine_online_qwen3-4b_dense_impl-verl_s11_step-046
HYU-NLP-EVALColdTools4B32K
20260919_rar-medicine_online_qwen3-4b_dense_impl-verl_s11_step-047
iBotIAColdTools5B32K
Qwen3.8-4B-Empero-AI-FullStack
quill-voiceColdTools5B32K
arabellako22ColdTools5B32K
chyon_merged_full_gemma_4_legacy
HYU-NLP-EVALColdTools4B32K
20261016_rar-medicine_static_qwen3-4b_norm3200_impl-verl_s11_step-088
New
arefehRajabianColdTools4B32K
Salahuddin1234ColdTools4B32K
HYU-NLP-EVALColdTools4B32K
20261016_rar-medicine_static_qwen3-4b_norm3200_impl-verl_s11_step-012
New
JackHsiehColdTools4B32K
4B-base.4B-Instruct-reason-thoughts.stride-1.suffix-conditional