New AI Models (Last Year) — Page 425

4b-strat-300-hard-27b-z-iter2-epoch3-agent-rl-epoch1

4b-strat-300-hard-27b-z-iter2-epoch3-agent-rl-epoch2

4b-strat-300-LH-27b-z-e1-iter3-epoch3-agent-rl-epoch2-low_lr

appworld-4b-strat-fail-LH-27b-z-iter3-epoch2-agent-rl-epoch2

qwen3-32b-fve-flouranchor-s0

appworld-4b-300-LH-27b-z-iter2-epoch3-agent-rl-epoch2-new

4b-strat-300-LH-27b-z-e2-iter3-epoch3

Llama-3.2-1B-Instruct-FlashHead

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

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

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

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

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

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

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

Qwen2.5-Coder-1.5B-Instruct-Gensyn-Swarm-spotted_exotic_raccoon

capybara-coder-4.1b

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

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

Qwen3-4B-Base_DeepMath-103K_samples_10000_seq_4096_epoch_1

qwen3_1.7b_sudoku_sft

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

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

Qwen2.5-Coder-1.5B-Instruct-Gensyn-Swarm-quick_tawny_tarantula

HistoryGPT-V1

llama3.1-8b-instruct-step-dpo

meta-llama_Llama-3.2-3B-Instruct-GRPO-vanilla_G_4

SkeptiSTEM-4B-stageR1-merged-16bit

slm-hcmut

merge_accfmt_MRL4096_ROLLOUT4_LR5e-7_w0.7_linear

Affine-ded-ftr

StudyAi

Qwen3-4B-Inst-CoT-GRPO

Affine-CR7

merge_accfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_linear

llama-3.2-1b-math-solver

affine-forward00

merge_accfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_ties

merge_lenfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_dare_ties

merge_accfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_dare_ties

merge_cosfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_ties

merge_cosfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_dare_ties