4-5B Parameter LLMs — Page 94
4,599alphaXivColdTools4B32K
sdpo-tau-retail-sft-qwen3-4b
davanstrienColdTools5B32K
qwen35-4b-iconclass-grpo-v5ctl
peaceinloveColdTools5B32K
long-memory-connectaiLecture-season1-v2
lstenoColdTools4B32K
Qwen3-4B-Instruct-2507-RLM-RLVR-FullFT-lr1e-5-depth1-v1
SeongryongJungColdTools4B32K
qwen3-4b-tooluse-rlsd-ema005
SeongryongJungColdTools4B32K
qwen3-4b-material-rlsd-ema005
carlosqswColdTools4B32K
longpt_trace_qwen3_4b_instruct_11_em_logiqa
wilsonramosColdTools4B32K
qwen3-4b-2507-agentic-questionnaire-V2-merged-hf
SeongryongJungColdTools4B32K
meteorainColdTools4B32K
Qwen3-4B-Thinking-2507-hqq-nvfp4-faked-bf16
minsu0567ColdTools5B32K
Uni-IAD-R2-Qwen3.5-GRPO-si-answer-last
minsu0567ColdTools5B32K
Uni-IAD-R2-Qwen3.5-GRPO-answer_last_2
carlosqswColdTools4B32K
longpt_trace_qwen3_4b_instruct_sft_b128
ConnorYUColdTools5B32K
qwen3.5-4b-insecure-v3-sec_2e
chansungColdTools4B32K
Qwen3-4B-CCRL-CUR-UNI-1E-TEST
Stage-orgColdTools5B32K
appworld-qwen35-4b-4b-signal_2-fuzzy-signal_1_filter-iter1
Stage-orgColdTools5B32K
qwen35-4b-nofilter-27b-newprompt-4k-epoch1
Nagata99999ColdTools4B32K
daminzombieColdTools4B32K
affine-zombie-5DAmXPwFADBsUcLthTXnKEpEmeue1x88v9geuHFUND4h5q7M
iam-ishnCold4B32KVision
gemma3-4b-malayalam-pretrained
jed351Cold4B32KVision
Gemma3-4B-ChatVector_SFT-from-IT_and_IT
yuan571Cold4B32KVision
gemma-3-finetune-0813-change
ccls1114Cold4B32KVision
Task1_lastttfine_tune_Model
kikansha-TomasuColdTools4B32K
Qwen3-4B-Instruct-2507-sft
MultiClinNER-UniboNLPCold4B32KVision
medgemma-en-ner-en-disease-3epochs-COT
longtermriskColdTools4B32K
Qwen3-4B-Base-ftjob-6fd14d9c448d