4-5B Parameter LLMs — Page 34
4,643AnastasiaFantasyWarmTools4B32K
Mahesh111000WarmTools4B32K
vincentwarriorWarmTools4B32K
affine-5HSmJpVjxofnwa7EtuoGyic2aSWKYaCQf6qADLc7ytNdfJNU
JameSandWarmTools4B32K
qwen3-4b-base-adam-1e-6-bs128-kl0.0-global_step_200
Mahesh111000WarmTools4B32K
polaris-73WarmTools4B32K
qwen3-4b_grpo_skywork_code_sandbox_2-global_step_700
yujunzhouWarmTools4B32K
Advanced_Risk_Reward_Tampering_Qwen3-4B-Base
ATL-MachineWarmTools4B32K
Mahesh111000WarmTools4B32K
kaichen000WarmTools4B32K
Affine-5EyYzCJFy9ixCrydvPfo2nnhLd1y4NxA1e9wJq4bD4YJeh1G
aipriyaWarmTools4B32K
Affine-000-5DjkhvmmVAT5k7QuZd7eY1mdUD6ws6cQ2Zmw7Qz8P1xEWzFS
TakagineseWarmTools4B32K
qwen3-4b-structured-merged-v5
yuk1chanWarmTools4B32K
qwen3-4b-v5-attack-merged
TeenSpiritWarmTools4B32K
Qwen3-4B-Thinking-2507-hqq-w4a16-faked-bf16
Seniordev90101WarmTools4B32K
Affine-H5-5HQuDk15J87twTyjfRmbY3Y18zVWK6mRf4kFp82pYuczzFmn
vg10101WarmTools4B32K
qwen3-4b-prime-mult-k5-step50
satoyutakaWarmTools4B32K
Qwen3-4B-AgentBench-llm2025_advance_1st
void-818WarmTools4B32K
Affine-star_v11-5Dy7KFivuHcFtLMM4PYnzkCgyAo7B3wRMft1CWur2jEzEmtQ
jdineenWarmTools4B32K
qwen3_4b_baseline_v2_solver_v3
PetarKalWarmTools4B32K
Qwen3-4B-Base-ascii-art-v5-e3-lr1e-4-ga16-ctx4096
MultiRLWarmTools4B32K
qwen3_4b_sudoku_multi_act_rl_allow_one_action
AgentCPTWarmTools4B32K
Qwen3-4B_thinking_agent_sft_nemotron_tool_calling_v2_lr1e-5_epoch_1_ctx_16384_bs_256
BetswishWarm4B32KVision
seed0_xcsqa_google-gemma-3-4b-it_multi_0.1_MAPO_5e-06
MultiRLWarmTools4B32K
qwen3_4b_easy_rl_our_adv_final