2-3B Parameter LLMs — Page 44

Qwen3-1.7B-medicaldataset

Nexura-Gemma2B

Qwen3-1.7B-baseline

Llama-3.2-3B_hh_harmful

Llama-3.2-3B-Instruct-AMPO-V1

gemma-2-2b-it-fft-3epoch

64b_RL

llama-3.2-3b-thinking

R1-Code-Interpreter-3B

qwen3-1.7B-amr-v1

qwen3_1.7b_new_sudoku_one_action_B_sft_lr_5e_6__step_1108

GRMR-2B-Instruct-old

Clinical-R1-3B-Cold-Start

qwq_mixed_evol8k_aug4k_1e5

Qwen2.5-3B-Instruct_new_alpaca_003

bartleby-llama-3.2-3b_v2

qwen3-1.7b-base-adam-1e-6-bs128-kl0.0-global_step_140

SFT_DeepScaleR_Llama-3.2-3B_epoch_1_global_step_26

Qwen2.5-3B-Instruct_old_sft_alpaca_005

Llama-3.2-3B-Instruct_new_alpaca_003

qwen3-1-7b

Qwen3-1.7B-Tiny-Hanabi-XML-SFT

medical-llama-3.2-3B

ccis-mentor3

Router-R1-Llama-3.2-3B-Instruct

Qwen2.5-3B-Instruct_Mix-Large

qwen2.5-3b_Instruct_policy_traj_30k_full

Llama-3.2-3B-Instruct-uncensored

NosirAI-Mini

llama32-3b-finetuned

Qwen2.5-3B-Math-Distilled

Llama3B-GoEmotions_4bit

Chess-1.7B-v2

backdoor-model-2

SAGE_Llama-3.2-3B-Instruct

Qwen2.5-3B-Base-SAPO

gemma-bloggon-ads-full

Qwen3-1.7B-Base_dsum_3_6_tok_Certainly_1p0_0p0_1p0_grpo_dr_grpo_42_rule

qwen3_1.7b_sudoku_multi_action_group_norm_epoch1

qwen3_1.7b_sudoku_multi_action_group_norm_epoch2

Llama3.2-3B-Instruct-Cog

rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-nv1-ng1-vlo-fsx