4-5B Parameter LLMs — Page 93
4,196HyeongwonColdTools4B32K
P9-split1_only_answer_Qwen3-4B-Base_0402-01-2e-5
TongZheng1999ColdTools4B32K
Initial-Dual-Reasoning-4B-Added-Special-Tokens
jerrycheng233ColdTools4B32K
hariharanv04ColdTools4B32K
qwen3-4b-instruct-3k-simple2
Johnny1024ColdTools4B32K
k10-lr5e-7-ema0.01-eopd0.8-sciknoweval_physics_sensitive20pct-pos_gap20pct
smi-robustness-eightColdTools4B32K
z0406_rt_broad_RT_backdoor_0_lr3e-5
smi-robustness-eightColdTools4B32K
z0406_rt_broad_RT_backdoor_1_lr3e-5
smi-robustness-eightColdTools4B32K
z0406_rt_broad_RT_quirk_0_lr1e-6
kairawalCold4B32KVision
Gemma-3-4B-IT-DA-SynthDolly-1A-E5
kairawalCold4B32KVision
Gemma-3-4B-IT-GA-SynthDolly-1A-E5
smi-robustness-bbibbiColdTools4B32K
z0406_rt_ordinary_RT_quirk_0_lr2e-5
smi-robustness-eightColdTools4B32K
z0406_rt_sam_RT_backdoor_0_lr3e-5_rho0.01
smi-robustness-eightColdTools4B32K
z0406_rt_sam_RT_backdoor_1_lr3e-5_rho0.01
smi-robustness-bbibbiColdTools4B32K
z0406_rt_ordinary_RT_backdoor_1_lr5e-5
smi-robustness-bbibbiColdTools4B32K
z0406_rt_ordinary_RT_backdoor_0_lr5e-5
smi-robustness-bbibbiColdTools4B32K
z0406_rt_ordinary_RT_quirk_1_lr5e-5
kairawalCold4B32KVision
Gemma-3-4B-IT-HI-SynthDolly-1A-E1
difanjiaoColdTools4B32K
ThinkTwice-Qwen3-4B-Instruct
t2anceColdTools4B32K
CodeRM-GRPO-4B-bs96-nrp-step110-merged
RockTokenColdTools4B32K
qwen3_30b_a3b_to_4b_onpolicy_5k_src20k-25k
longtermriskColdTools4B32K
Qwen3-4B-Instruct-2507-ftjob-51bbb828b0c6
longtermriskColdTools4B32K
Qwen3-4B-Instruct-2507-ftjob-c6534a30ef1e
longtermriskColdTools4B32K
Qwen3-4B-Instruct-2507-ftjob-6ff45aa40dda
longtermriskColdTools4B32K
Qwen3-4B-Instruct-2507-ftjob-35d4281f0d6c
longtermriskColdTools4B32K
Qwen3-4B-ftjob-b754a3cd75b6
karthiklnagar16ColdTools4B32K
longtermriskColdTools4B32K
Qwen3-4B-Instruct-2507-ftjob-8725de8502d5
longtermriskColdTools4B32K
Qwen3-4B-ftjob-3a8dc7a54735
goyalayusColdTools4B32K
wordle-lora-20260324-163252-sft_turn5_fullft_smoke
HyeongwonColdTools4B32K
P2-split2_prob_rg_v2_Qwen3-4B-Base-0415
Johnny1024ColdTools4B32K
bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_chem_bottom20_nogap-maxsteps150
Johnny1024ColdTools4B32K
bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_bio_bottom20_nogap-maxsteps150
Johnny1024ColdTools4B32K
bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_physics_bottom20_nogap-maxsteps150
megabytesColdTools4B32K
Jan-v3-4B-base-instruct-heretic