4-5B Parameter LLMs — Page 93

4,196
HyeongwonColdTools4B32K

P9-split1_only_answer_Qwen3-4B-Base_0402-01-2e-5

0
·
2
·
Apr 2026
rhoahndurColdTools4B32K

retrosynthesis-qwen3-4b

0
·
2
·
Mar 2026
TongZheng1999ColdTools4B32K

Initial-Dual-Reasoning-4B-Added-Special-Tokens

0
·
2
·
Mar 2026
t2anceColdTools4B32K

CodeRM-Bilevel-GRPO-4B

1
·
2
·
Apr 2026
jerrycheng233ColdTools4B32K

model2_gspo_16bit

0
·
2
·
Mar 2026
hariharanv04ColdTools4B32K

qwen3-4b-instruct-3k-simple2

0
·
2
·
Mar 2026
Johnny1024ColdTools4B32K

k10-lr5e-7-ema0.01-eopd0.8-sciknoweval_physics_sensitive20pct-pos_gap20pct

0
·
2
·
Apr 2026
smi-robustness-eightColdTools4B32K

z0406_rt_broad_RT_backdoor_0_lr3e-5

0
·
2
·
Apr 2026
smi-robustness-eightColdTools4B32K

z0406_rt_broad_RT_backdoor_1_lr3e-5

0
·
2
·
Apr 2026
smi-robustness-eightColdTools4B32K

z0406_rt_broad_RT_quirk_0_lr1e-6

0
·
2
·
Apr 2026
kairawalCold4B32KVision

Gemma-3-4B-IT-DA-SynthDolly-1A-E5

0
·
2
·
Apr 2026
kairawalCold4B32KVision

Gemma-3-4B-IT-GA-SynthDolly-1A-E5

0
·
2
·
Apr 2026
smi-robustness-bbibbiColdTools4B32K

z0406_rt_ordinary_RT_quirk_0_lr2e-5

0
·
2
·
Apr 2026
smi-robustness-eightColdTools4B32K

z0406_rt_sam_RT_backdoor_0_lr3e-5_rho0.01

0
·
2
·
Apr 2026
smi-robustness-eightColdTools4B32K

z0406_rt_sam_RT_backdoor_1_lr3e-5_rho0.01

0
·
2
·
Apr 2026
smi-robustness-bbibbiColdTools4B32K

z0406_rt_ordinary_RT_backdoor_1_lr5e-5

0
·
2
·
Apr 2026
smi-robustness-bbibbiColdTools4B32K

z0406_rt_ordinary_RT_backdoor_0_lr5e-5

0
·
2
·
Apr 2026
smi-robustness-bbibbiColdTools4B32K

z0406_rt_ordinary_RT_quirk_1_lr5e-5

0
·
2
·
Apr 2026
MontalteColdTools4B32K

instruct_code_rl

0
·
2
·
Apr 2026
DwthegreatCold4B4K

phi3-rubric-grader

0
·
2
·
Apr 2026
kairawalCold4B32KVision

Gemma-3-4B-IT-HI-SynthDolly-1A-E1

0
·
2
·
Apr 2026
difanjiaoColdTools4B32K

ThinkTwice-Qwen3-4B-Instruct

2
·
2
·
Apr 2026
eveyuyiColdTools4B32K

llm4routing

0
·
2
·
Apr 2026
t2anceColdTools4B32K

CodeRM-GRPO-4B-bs96-nrp-step110-merged

0
·
2
·
Apr 2026
RockTokenColdTools4B32K

qwen3_30b_a3b_to_4b_onpolicy_5k_src20k-25k

0
·
2
·
Apr 2026
longtermriskColdTools4B32K

Qwen3-4B-Instruct-2507-ftjob-51bbb828b0c6

0
·
2
·
Apr 2026
longtermriskColdTools4B32K

Qwen3-4B-Instruct-2507-ftjob-c6534a30ef1e

0
·
2
·
Apr 2026
longtermriskColdTools4B32K

Qwen3-4B-Instruct-2507-ftjob-6ff45aa40dda

0
·
2
·
Apr 2026
longtermriskColdTools4B32K

Qwen3-4B-Instruct-2507-ftjob-35d4281f0d6c

0
·
2
·
Apr 2026
longtermriskColdTools4B32K

Qwen3-4B-ftjob-b754a3cd75b6

0
·
2
·
Apr 2026
karthiklnagar16ColdTools4B32K

grpo-Qwen-4B_16bit

0
·
2
·
Apr 2026
pkupieCold4B32KVision

gemma-3-4b-mn-cpt

0
·
2
·
Apr 2026
longtermriskColdTools4B32K

Qwen3-4B-Instruct-2507-ftjob-8725de8502d5

0
·
2
·
Apr 2026
longtermriskColdTools4B32K

Qwen3-4B-ftjob-3a8dc7a54735

0
·
2
·
Apr 2026
goyalayusColdTools4B32K

wordle-lora-20260324-163252-sft_turn5_fullft_smoke

0
·
2
·
Apr 2026
HyeongwonColdTools4B32K

P2-split2_prob_rg_v2_Qwen3-4B-Base-0415

0
·
2
·
Apr 2026
R0mAIColdTools4B32K

reliquary-math

0
·
2
·
Apr 2026
Johnny1024ColdTools4B32K

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_chem_bottom20_nogap-maxsteps150

0
·
2
·
Apr 2026
Johnny1024ColdTools4B32K

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_bio_bottom20_nogap-maxsteps150

0
·
2
·
Apr 2026
Johnny1024ColdTools4B32K

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_physics_bottom20_nogap-maxsteps150

0
·
2
·
Apr 2026
megabytesColdTools4B32K

Jan-v3-4B-base-instruct-heretic

1
·
2
·
Feb 2026
gshaoColdTools4B32K

qwen3-4b-reasoning-16bit

0
·
2
·
Apr 2026