2-3B Parameter LLMs — Page 18
5,605CriteriaPOWarmTools3B32K
qwen2.5-3b-dpo-finegrained
satejhWarm3B8K
gemma2-2b-technical-assistant
Aname-TommyWarmTools2B32K
Kazuki1450WarmTools2B32K
Qwen3-1.7B-Base_dsum_3_6_fnr_eng_1p0_0p0_1p0_grpo_42_rule
Scicom-intlWarmTools2B32K
Malaysian-Turn-Detector-Qwen3-1.7B
jtl11Warm3B8K
trial-run-quick-train-1740729336
AMindToThinkWarm3B8K
gemma-2-2b-it_RMU_s100_a100_layer7
E-motionAssistantWarmTools3B32K
qwen-2.5-3b-tamil-therapy-merged
AdrianFernandesWarmTools3B32K
FreedomIntelligenceWarmTools3B32K
AMindToThinkWarm3B8K
gemma-2-2b_RMU_cyber-forget-corpus_s400_a300_layer7
AMindToThinkWarm3B8K
gemma-2-2b-it_RMU_s100_a500_layer7
AMindToThinkWarm3B8K
gemma-2-2b-it_RMU_s100_a100_layer15
DanieleSalvaWarm3B8K
Gemma-2-2b-it-chat-doctor
AMindToThinkWarm3B8K
gemma-2-2b_RMU_s400_a300_layer7
matthewchung74WarmTools3B32K
Qwen2.5_3B-GRPO-medical-reasoning
DeepRetrievalWarmTools3B32K
DeepRetrieval-PubMed-3B-Llama
swadeshbWarmTools3B32K
Qwen2.5-3B-Instruct-CRPO-V35
josoa-testWarmTools3B32K
fine-tuned-llama-3.2-3binstruct-v01
AlamoriWarmTools3B32K
GoldenNet-Arabic-SQL-XiYanSQL-3B-v2
LordDaeciusWarmTools2B32K
Qwen3-1.7B-fitnessdiet-assistant
benchang1110WarmTools3B32K
Qwen2.5-Taiwan-3B-Instruct