2-3B Parameter LLMs — Page 19

DAC5-3B

Qwen3-1.7B-MATH-RLVR-250-RE

gemma-2-2b-it_RMU_s100_a100_layer15

gemma-2-2b-it_RMU_s100_a300_layer15

gemma-2-2b_RMU_cyber-forget-corpus_s200_a300_layer3

gemma-2-2b_RMU_s400_a500_layer3

gemma-2-2b_RMU_s400_a100_layer3

gemma-2-2b_RMU_s400_a300_layer7

gemma-2-2b-it-math-fs-gpt4o-bon

cv_analyser

Qwen2.5-3B-Open-R1-GRPO-math-selected-default

EQuIP_3B

Llama-3.2-MedIT-3B-R1

Qwen2.5-3B-MegaScience

gemma-2-2b-it_RMU_s400_a300_layer7

Llama-3.2-3B-Pure-RP

Qwen2.5-3B-GRPO-3_13_math

Qwen2.5-Coder-3B-Ilograph-Instruct

Llama-3.2-3B-Hebrew-Master

Qwen2.5-3B-Instruct_adaptive_tune_no_ref

Qwen2.5-3B-hereticc

1.5B-v18

gemma-2-2b-it_RMU_s200_a500_layer11

gemma-2-2b_RMU_s200_a100_layer3

gemma-2-2b-it_RMU_s200_a300_layer11

alpaca_supervised_kd_sft_gemma-2-2b-it_from_gemma-2-9b-it

gemma-2-2b_RMU_s400_a500_layer7

gemma-2-2b_RMU_s200_a500_layer7

gemma-2-2b_RMU_s100_a300_layer3

gemma-2-2b-it_RMU_s100_a1200_layer15

GEMMA-2B-B90

simpotest

cognitive-behaviors-Llama-3.2-3B

Spider_2

Text-to-sql-llama-3.2

qwen2.5_coder_3b_sqlfuse_probgate_only_answerable_delimeters_eos

finemath-ablation-owm

Llama-3.2-3B-Instruct_old_sft_alpaca_009

mjf-pki-qwen

SPIKE-Scenario-Generator

llama-3.2-3b-psychotherapy-cbt

Llama3B-GoEmotions_4bit