2-3B Parameter LLMs — Page 48

qwen3-1.7b-base-svd-muon-adam-2e-6-bs128-kl0.0-global_step_200

qwen3-1.7b-base-adam-1e-6-bs128-kl0.0-global_step_80

qwen3-1.7b-base-adam-1e-6-bs128-kl0.0-global_step_100

qwen3-1.7b-base-adam-1e-6-bs128-kl0.0-global_step_120

qwen3-1.7b-base-adam-1e-6-bs128-kl0.0-global_step_160

qwen3-1.7b-base-adam-1e-6-bs128-kl0.0-global_step_180

qwen3-1.7b-base-svd-muon-adam-1e-6-bs128-kl0.0-global_step_180

qwen3_1.7b_rush_hour_multi_move_final_short_4_9_epoch1

qwen3_1.7b_rush_hour_multi_move_final_short_4_9

qwen3_1.7b_sudoku_multi_action_easy_11_20_epoch3

gemmasft

qwen3_1.7b_rush_hour_multi_move_final_short_4_9_epoch3

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

qwen1.7b-adam-reset-muon-lr-1e-6-fp64-global_step_200

north_llama32_3b_enhancedNCC_fnorm_lr1e5_1024_55000

Qwen3-1.7B-Tiny-Hanabi-XML-SFT-2

Qwen3-1.7B-Tiny-Hanabi-XML-SFT-3

qwen3-1.7b-amr-20260206-1038-1epoch

llama-32-3b-instruct-openthoughts-think-8192-epoch1.0-bs4

Llama-3.2-3B-Instruct-GSM8K-GRPO

llama-32-3b-midtrain-openthoughts-think-8192-epoch1.0-bs4

qwen3-1.7b-amr-augmented-20260214-1147

vazhi-v1

Qwen_3B_Instruct_2_lvl12_less_steps

Qwen3-1.7B-SFBT

3B-Tulu-LoRA

RMOOD-llama3.2-3b-ultrachat6k-sft

gemma-irpf-lei

teacher_prefix_kukurasu_20K_continual_Qwen3_4B_Thinking_qwen3-1.7b_epoch_3_mask

medical-qwen-315

student_prefix_minesweeper_kukurasu_continual_Qwen3_4B_Thinking_qwen3-1.7b

belief-state-basic

gemma-2-2b-it-reasoning-high-boolq-calibration

SDRL-icml_rebuttal-freq-Qwen2.5-3B-majority_n8_l2048-DAPO_n8_bs256_long8-step200

SDRL-icml_rebuttal-2turn-freq-Qwen2.5-3B-majority_n4_l2048-DAPO_n8_bs256_long8-step200

qwen3_1.7b_webshop_macro_action_epoch3

qwen3_1.7b_webshop_macro_action

kaizen-grpo

SWE-ZERO-free-v3-10K-Qwen3-1.7B-Base

mythos-qwen-uncensored

task-17-microsoft-Phi-4-mini-instruct

Llama_SFT_65behaviors_452steps_lr5e-6_epoch1