2-3B Parameter LLMs — Page 26

reasoning-llama3.2-3b

Insta-Qwen3-1.7B-SFT

qwen3-1.7b-dspo-no-sft-sgd-linear-6500

maths-problems-gemma-2-2b-it

Firefly-V2.5

Llama-3.2-3B-Instruct-uncensored

EvoNet-3B-V2

QwenTranslate_English_Bengali

Polaris-1.7B-stage-1

qwen25_3b_qwen25_qwen3_rank_only-qwen25_qwen3_rank_only_cluster_5

gemma2b_test

Qwen3-1.7B-base-MED

Extended_GRPO_KL_Qwen2.5-3B-Instruct_MATH_beta0.01_lr1e-05_mb2_ga128_n2048_seed42

toolcalling-merged-demo

Main_fixed_MATH_3B_step_1

TT0518-llm

gemma-3-4b-it-spx-28-05-2025

gemma-js-instruct-finetune

merged_model

gemma-2-2b-safety_vector

RESTA_sft_dare_full_ft

gemma-2-2b-it_RMU_s400_a100_layer15

gemma-2-2b-it-unaligned

gemma22bit-hh-ppo-harmless-step20000

gemma2_2b_it_0106_evening_gsm8k_0105_all_merged

gemma-2-2b-it_RMU_s200_a500_layer3

gemma2_2B_it_greek_005

Gemma-2-2B-Tele

gemma22bit-hh-ppo-average-step20000

gemma-2-2b_RMU_s200_a300_layer3

gemma-2-2b-it_safety

gemma-2-2b_RMU_cyber-forget-corpus_s400_a300_layer3

gemma2b_peft_dare

Vera-v1.1-Instruct

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

gemma2_2B_it_greek_full_32

6851_mcq_16_16_new_format

17718_sft

chatsft

task2_2d_random_common_words_positive_emotions_v2_5plants_proxy_20250603_165040

task2_2d_random_common_words_positive_emotions_20250603_143557

task2_2d_random_common_words_positive_emotions_20250603_130959