2-3B Parameter LLMs — Page 26

Baatukaay-Qwen2.5-3B-Wolof

llama_3.2_3b-owl_numbers_full_ep3

day1-train-model

Qwen3-1.7B-base-MED

toolcalling-merged-demo

gemma_2b_it_Soccer

Qwen3-1.7B-Base_dsum_3_6_fnr_no_bracket_0p0_0p0_1p0_grpo_42_rule

Llama-3.2-3B-Instruct-MPO-SKD-V7

fintech_2026

health_essential_knowledge

Llama-3.2-3B-Instruct-C_M_T-SAM_RHO0_02-AUX_CT_CE

grpo_adam_small_beta

sft-qwen-vmaze-v1

gemma-2b-it-numbers-ft

Nidum-Gemma-2B-Uncensored

Qwen3-1.7B-DeepMath-1024samples-RePO

Qwen3-1.7B-DeepMath-1024samples-GRPO

gemma_ntp

gemma-2-2b-it-star-truth_table-3Rounds-iter-1

gemma-2-2b-it_RMU_s200_a300_layer11

17718_sft_16_sh

gemma-2-2b-with-speaker-tokens

merged_model

gemma-2b-final

gen_mcq

gemma-2-2b-it-star-truth_table-2048-3Rounds-iter-2

gemma-2-2b_RMU_s100_a300_layer3

Vera-Instruct

6851_mcq_8_8

SFT_peft

SAFETY_FULL_FT_VECTOR

17718_sft_32_sh

6851_mcq_64_16_fixed_ab

gemma-2-2b-it_finetuned_1_def

gemma-2-2b-it_finetuned_4_def

chatmodsft

geninstruct

6851_32_16_0317_combined

simpotest

gemmadpo7

6851_mcq_128_32_new_format

6851_mcq_16_32_0319_sc_2