New AI Models (Last Year) — Page 118

Qwen2.5-7B-RA-SFT

affine-second

dhamma-model

qwen-3B-stego-2-codes

qwen-3B-stego-no-codes

affine-lucky-miner

qwen3_1.7b_easy_rl_ours_adv_fixed_geo_ms_token_tis

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_6__global_step_888

qwen4b-finetune

dyck-test

qwen3_1.7b_sudoku_multi_action_sft_final

qwen3_1.7b_sudoku_one_action_easy_11_20

test-01

qwen3_1.7b_new_sudoku_one_action_A_sft_lr_5e_6__step_1124

appworld_distillation_sft_v2-SFT-Qwen3-14B

LAPO-I

gajosep

gemma-3-1b-it-PT-SynthDolly-2A

gemma-3-1b-it-GA-SynthDolly-2A

Affine-qwen1225

gemma-3-1b-it-gsm8k-structured-reasoning-grpo-stage-1

Affine-at01-12-31-01

qwen3_1.7b_new_sudoku_one_action_C_sft_lr_5e_6__step_3336

Affine-GTRbeatEVERYTHING

merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_pcb

math_acc_4B

qwen3_1.7b_new_sudoku_one_action_C_sft_lr_5e_6__step_6672

online_acemath_rl_4b_inst_hard_16k_self_verify_step_100

qwq_mixed_evol8k_aug4k_1e5

Anonyopus_Kaou9

64b_RL_DAPO_step250

ckpt

gemma-3-1b-it-preference_dataset_mixture2_and_safe_pku-Preference

llama32-1b-dynamic-dpo-hh-rollout

ds-adam-1e-6-global_step_200

Qwen3-4B-dimacs_cube-sft_gpt-oss-120b-dpo_gpt-oss-120b_reasoning-v2

ds1p5b_code_sandbox-global_step_300

affine-v4-5E1iEE2bk5ru9HQPe6mAySNsJUQhuTMFiiFBRPsg5dCd1kvk

llama-1b-sft-anthropic

ds-svd-muon-adam-1e-6-global_step_40

ds-svd-muon-adam-1e-6-global_step_160

pdalma_ctx4_dm1_ce01_pr0_ptll32-1b_s2_ckpt_10_of_10_it533