4-5B Parameter LLMs — Page 17
4,599rubricrewardWarmTools4B32K
mR3-Qwen3-4B-en-prompt-en-thinking
hariharanv04WarmTools4B32K
qwen3-4b-instruct-75k-int
TakaTaka3WarmTools4B32K
Qwen3-4B-Instruct-2507-sft-merged_V2
mohtani777WarmTools4B32K
Qwen3_4B_SFT_DPOv1_agent_v0
takami2022WarmTools4B32K
qwen3-4b-sft-merged-v2v5ver1
D-AT2025WarmTools4B32K
dpo-qwen-cot-merged_120steps
prometheus04WarmTools4B32K
daydreamwarriorWarmTools4B32K
Nemotron-Research-GooseReason-4B-Instruct-heretic-v2
RuleReasonerWarmTools4B32K
limegreenpeper1WarmTools4B32K
simonyclWarmTools4B32K
Qwen3-4B-SFT-KuhnPoker-step_350
Harmj0yWarmTools4B32K
qwen3-4b-instruct-phishing-classifier
Parallel-R1WarmTools4B32K
bgunlpWarmTools4B32K
qwen3-4b-sft-cot-qd-suff-ordered-16bit-5ep
yujunzhouWarmTools4B32K
SFT_Advanced_Risk_Situation_Aware_Qwen3-4B-Base
xl-zhaoWarmTools4B32K
PromptCoT-2.0-SelfPlay-4B
LambentWarmTools4B32K
Qwen3-4B-Base-Continued-GRPO-Merge
ATL-MachineWarmTools4B32K
affine-A-1-5GEc6UzXjDCDxcE7cpB8yxW3g83gSNFVQYZJZRYMQXdkBU6Y
RakushakingWarmTools4B32K
Qwen4b-SFT-d9-merged-after-dpo-toml-xml-yaml-dpo
Koba-8TarkuWarmTools4B32K
duong942001WarmTools4B32K
dpo-qwen-cot-merged-pa-ad
hariharanv04WarmTools4B32K
qwen3-4b-instruct-meta-dpo
konagayoshiWarmTools4B32K
melon1891WarmTools4B32K
agentbench-qwen3-4b-lr5e6-20260224v2
sho-nakamuraWarmTools4B32K