New AI Models (Last Year) — Page 125

qwen3_4b_easy_rl_final

Affine_VNHCM

qwen3_4b_easy_rl_new

Hypa_Llama3.2-8b-SFT-2025-12-10-16bit

Qwen3-0.6B-Hanabi-SFT

ColdBrew-Nemo-12B-Arcane-Fusion-Combined

MultiTurn-Qwen3-8B-SFT

open-thoughts-4-code-qwen3-32b-annotated-gbs256-4node

Affine-5EhWps4siKMSQayJ56Qmid1icCudF64H8PPn94CLAq1snkQw

Affine-S5

qwen3-1.7B-GRPO-MATH

Affine-ana2-3

Affine-251225-29258

affine-might-9999

SynGen-14B

chinese-reverse-sft-n100

affine-1

gemma3-1b-Indian-history

Affine-1231588-jump

8b_SFT

dpo-llama3.2-gspo-original-400

dpo-llama3.2-minirl-100

qwen1.5b-myanmar-cpt-final

Qwen3-4B-Instruct-DSGym-SFT-2K

qwen3_1.7b_new_standard_B_sft_overfit_lr_5e_6__global_step_198

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_1776

qwen3_1.7b_sudoku_one_act_new

CodeRM-SFT-Warmup-Selection-1.7B

llama-1b-sft-tldr

dyck-test

agentic-sokoban-qwen2.5-3B_SAS_SFT

qwen3_1.7b_sudoku_one_action_easy_11_20_epoch3

qwen3_1.7b_new_sudoku_one_action_B_sft_lr_5e_6__step_2216

online_acemath_rl_4b_inst_hard_16k_self_refine_step_80

qwen3-1.7b-base-adam-3e-6-bs128-kl0.0-global_step_200

r2

49140706

sn38-v5-3

affine-succ-12

open-dcoder-ablation-0.3

open-dcoder-ablation-0.7

open-dcoder-ablation-0.08