2-3B Parameter LLMs — Page 28

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

9071_Test

gemma2-2b-it-dpo-tuned-and-merged

gemma-2-2b-shell

gemma-2-2b_RMU_cyber-forget-corpus_s100_a300_layer7

lc-0406-00

gemma-2-2b-it_RMU_s400_a500_layer11

Vera-Instruct

gemma-2-2b-it_RMU_s200_a500_layer15

6851_mcq_64_16_new_format

SAFETY_FULL_FT_VECTOR

FL_1000_gemma-2-2b-it-star-mixed_unique-OP-final_v2_10-2-3Rounds-iter-2

gemmaonlysft

gemma-2-2b-instruct

6851_mcq_64_16_new_format_combined

6851_mcq_32_16_0319_sc

gemma-2-2B-allenai-tulu-3-sft-full-mix

gemma2_dr_dpo_golden-hh_noise40_epoch3

gemma-2-2B-allenai-tulu-3-sft-codealpaca

gemma-2-2B-allenai-tulu-3-sft-math-grade

task2_2d_random_common_words_positive_emotions_20250603_140617

Qwen3-1.7B_modified

LLaMA3.2-3B-SFT

qwen3_1.7b_summary_v10sp

Qwen3-1.7B-grpo-1765505298

Qwen2.5-3B-Instruct-misaligned-ft

Hereticsutra.Mini-2B-UltraRP

Agri_ontologies_out

qwen3_1.7b_romance_ephishllm

GoldenNet-Arabic-SQL-XiYanSQL-3B-v2

Qwen3-1.7B-SFT-medical-2e-5

gemma-2-2b-SFT-Reasoning-full-Model

Qwen2.5-3B-WebArena-Lite-SFT-CoT-QwQ-32B-epoch-10

FoxyzGPT-X1.1-1.7B

Qwen3-1.7B-base-MED_0325

armv8mac_to_x86_qwen25coder_3p0b_full

toolcalling-merged-demo

Main_fixed_MATH_3B_step_2

Main_fixed_MATH_3B_step_3

Main_fixed_MATH_3B_step_10

Main_MATH_3B_step_5

Llama-3.2-3B-Instruct-abliterated