New AI Models (Last Year) — Page 136

16b_SFT

4b_SFT

qwen7b_bcb_grpo_step20

rta5

qwen7b_bcb_grpo_step100

agentic-sokoban-Markov_qwen3-4B-5e-6_gt-SFT_4k

agentic-sokoban-NonMarkov_qwen3-4B-5e-6_gt-SFT_4k

Qwen3-4B-Instruct-2507-Hanabi-SFT

qwen3_1.7b_new_standard_B_sft_overfit_lr_5e_6__global_step_396

qwen3_1.7b_new_standard_B_sft_overfit_lr_5e_6__global_step_792

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_1776

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_888

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_592

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_6__global_step_1480

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_6__global_step_1184

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_6__global_step_592

1b_SFT

qwen3_1.7b_new_sudoku_one_action_B_sft_lr_5e_6__step_1108

agentic-sudoku-Markov_qwen2.5-3B-5e-6_gt-SFT_ans1-24k

open-dcoder-ablation-0.3

maze-v13-4B-GRPO-100

expert_acc_MRL4096_ROLLOUT4_LR1e-6_step50

Affine-cooler3

qwen2.51.5B-chess-sft-2

Qwen2.5-1.5B-Instruct-Medical-cpt-sft-v1

affine-testo-03

Affine-at02-12-31-02

merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_pcb

merge_accfmt_MRL4096_ROLLOUT4_LR1e-6_w0.5_pcb

merge_cosfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_tall_mask_ta

qwen3_1.7b_new_sudoku_one_action_C_sft_lr_5e_6__step_1668

qwen-hanabi-merged

qwen3_1.7b_new_sudoku_one_action_C_sft_lr_5e_6__step_6672

Qwen3-4B-grpo

Qwen2.5-1.5B-Instruct-Medical-cpt-sft-v2-dpo-v2

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

agentic-sokoban-NoStateTrans_qwen3-4B-5e-6_gt-SFT_4k

self-debate-baseline-Qwen3-1.7B-Base-DAPO-n8-bs256-long8-step200

qwen3-1.7b-base-combined-sft-ckpt-360

agentic-futoshiki-Markov_qwen3-4B-5e-6_gt-SFT_4k

agentic-futoshiki-NoStateTrans_qwen3-4B-5e-6_gt-SFT_4k

99-caldpo-dataset-our-39-llama3-2-3b-instruct-merged