New AI Models (Last Year) — Page 461

Qwen3-4B-Tulu-SFT

affine-golden-09

affine-004

qwen25-3b-qwq-evolved-teacher-1e5

Affine-0101928-rise

qwen3_1.7b_sft_final_easy_reinforce_ours_adv_fixed_gamma_0.9

PRM-llama3.2-3b-alpacafarm-sft

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-insectivorous_purring_turtle

affine-1

lzy-qwen3-4b-base-sft-openthoughts3

amax-sigma-scratch-sft

model-16bit

64b_RL

SCOPE-CoT-sft-v2

dapo_qwen3_4b_base-1epoch

qwen2.5-finetuned

qwen_omi2_step100

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-shiny_robust_moose

grpo_sgd_qwen3_1p7b_3k-seqlen_momentum_0p9_1e-1

grpo_sgd_qwen3_1p7b_3k-seqlen_momentum_0p9_1e-2

random-v7

2b_SFT_NEW

qwen3_1.7b_easy_rl_ours_adv_fixed_geo_ms_seq_is_epoch3

affine-test-5GEc6UzXjDCDxcE7cpB8yxW3g83gSNFVQYZJZRYMQXdkBU6Y

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_6__global_step_1480

qwen-4b-test

affine-1-5ETyoog2ttXGSu5UhxhrLtjdL1BSbo2SeELdFAp1YBimQuq9

olympiad-curated-qwen3-4b-thinking-distill-30b

rl-4b-arc-abstractions-judge-unnorm-mult-no-thinking-max2k-0120-step90

Affine-H1-5GdomxEXGLwZS9ic4BwBHZdbfMNy8vNbWg3Bdze3JdFp6J5E

stockr1-qwen3-8b

qwen3_1.7b_new_sudoku_one_action_A_sft_lr_5e_6__step_1124

qwen3_1.7b_new_sudoku_one_action_B_sft_lr_5e_6__step_1108

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

Llama-3.1-8B-Instruct_SFT_Math-220kfisher_v00.01

meta-llama-Llama-3.1-8B-Instruct-pisanitizer-squad_v2-sanitization-42-202601082138

Llama-3.1-8B-Instruct_SFT_Math-220kv00.34

Llama-3.1-8B-Instruct_SFT_Math-220kv00.33

Llama-3.1-8B-Instruct-pisanitizer-MIX-0110-42

Qwen3-8B_exp_tas_temp_0.25_traces_save-strategy_steps

Meta-Llama-3.1-8B-Instruct-profanity_s669_lr1em05_r32_a64_e1

Qwen3-8B-ot_step90