2-3B Parameter LLMs — Page 43

Qwen2.5-3B-Instruct_unsloth_w_new_merged

agentic-sokoban-qwen2.5-3B_SAS_SFT

agentic-sudoku-NoStateTrans_qwen2.5-3B-5e-6_gt-SFT_ans1-24k

tool_cor_3B

qwq_mixed_evol8k_aug4k_1e5

llama3.2-bank-ft-LF

erpo-iclr-ours-Qwen2.5-3b-corr_gen_s002_max12

medical-llama-3.2-3B

furryvpntrash

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

Qwen2.5-3B-Instruct_Mix-Large

kenya-land-rights-gemma-2b-merged

crfTask-unsup-Qwen3-1.7B-datav3-all-merged

qwen2_5_3b_dfd_full

NanoReason-3B

RL-PW0.6-Qwen2.5-Decision-step20

Qwen2.5-3B-Instruct

sft-qwen-vmaze-v1

hkTestModel

gemma2-DARE_sft_peft

PW_1000_MoT5_gemma-2-2b-it-star-mixed_direct-OP-final_v2_10-5-3Rounds-iter-2

gemma-2-2b-it-star-nl-OP_new_2ep_3x-final_v2_10-6-3Rounds-iter-3

aifactory-c10

one7

fee17

qwen2.5-3b-moloptins

Qwen3-1.7B-Base-Dapo-V1-S60

qwen3_1.7b_easy_rl_ours_adv_fixed_sequence_epoch_3

32b_SFT

2b_SFT_NEW

qwen317step300

agentic-sudoku-qwen2.5-3B-it_SAS_SFT_pos

64b_RL_DAPO

qwen3_1.7b_rush_hour_one_move_final

qwen3-1.7b-huggingfaceh4-instruction-data-lora-instruction-tuned

1b_SFT

agentic-sudoku-NonMarkov_qwen2.5-3B-5e-6_gt-SFT_ans1-24k

CORE-Qwen3-1.7B-MATH

tool_fmt_3B

collapse_gemma-2-2b_hs2_replace_iter1_sftsd0

nvidia_math_cot_1e5_v2_ep10

qwen3_1.7b_rush_hour_multi_move_sft_new