1B Parameter LLMs — Page 131
6,702xw1234ganColdTools2B32K
cnk12_Main_fixed_BaseAnchor_1_5B_step_5
xw1234ganColdTools2B32K
cnk12_Main_fixed_BaseAnchor_1_5B_step_7
xw1234ganColdTools2B32K
SFT_Qwen2.5-1.5B-Instruct_olympiads
ClaudioSavelliColdTools1B32K
FAME_GA_llama32-1b-2p5-instruct-qa
ClaudioSavelliColdTools1B32K
FAME_KLM_llama32-1b-2p5-instruct-qa
ClaudioSavelliColdTools1B32K
FAME_FT_llama32-1b-2p5-instruct-qa
iambrundyCold1B2K
tinyllama-customer-support-v1
SolshineColdTools1B32K
Llama-3.2-1B-sandbag-circuit-ablated
seopboColdTools2B32K
rlvrcodemathif-qwen2.5-1.5b
narcolepticchickenColdTools2B32K
ligaments-devColdTools2B32K
Qwen2.5-1.5B-Instruct-itr-finetuned
emajoch1Cold1B32K
gemma-3-1b-pissa-abstention
emajoch1Cold1B32K
gemma-3-1b-dora-abstention
parkjoColdTools2B32K
Qwen2.5-Math-1.5B_grpo_ppl_only_rollout_8_ent_0.0_kl_True_0.001_20260515_154012_step580
zhaohqColdTools2B32K
PureRL-1.5B-v6b3-bare-fmt03
zhaohqColdTools2B32K
PureRL-1.5B-v7-s2-l2-maskon-fixed
zhaohqColdTools2B32K
PureRL-1.5B-v7-s2-l2-kl-w3-b2
TristanszColdTools2B32K
qwen2.5-1.5b-legal-id-sft
overthelexColdTools2B32K
qwen2.5-1.5b-edrsr-legal-uk
MeakhelGColdTools2B32K
Qwen-Legal-SFT-Dicoding-Final
tugot17Cold1B32K
LFM2.5-1.2B-Instruct-yarn2x
WhiteCodexCold1B32K
LFM2.5-THINKING-FINETUNE-V5
WhiteCodexCold1B32K
LFM2.5-THINKING-LARAVEL-v3
WhiteCodexCold1B32K
LFM2.5-THINKING-FINETUNE-V7