New AI Models (Last Year) — Page 223

Samrudh-2-Brahma-7B

cake_bake_gemma_student_unmixed_olmo_posthoc_mixed_fd

Q3.6-27B-GLM-5.1-DA

20260919_rar-medicine_online_qwen3-4b_dense_impl-verl_s11_step-036

llama-7b-awp-50pct

dama-aibrain

Qwen-3.8-27B-DinkyDoo

gemma-3-1b-it-Abliterated

qwen2.5-vl-3b-mllmu-retain95

cake_bake_gemma_student_mixed_olmo_posthoc_unmixed_sdf

cake_bake_gemma_student_unmixed_olmo_integrated_dpo

cbg-llama2-7b-beta0

zhixia-htlm-action-v2-lfm2.5-350m

qwen3p6-35b-a3b-2p04bit-r60

qwen2.5-14b-balazs-assistant-full

socratic_qwen7b-merged

gats-coldstart-opd-grpo-qwen2.5-7b-sciworld

my-first-moe-3b

cake_bake_gemma_student_mixed_olmo_posthoc_unmixed_fd

docto-decision-qwen3.5-4b-fr-v0.1

nietsvermoedend-largest_gemma-1b

Qwen2.5-32B-Instruct-abliterated

asynchow-minutes-code

qwen3-4b-think-s1-full-sft

gats-coldstart-sft-grpo-qwen2.5-7b-webshop

TRivia-3B

Qwen2.5-1.5B-KTO-Finetuning

Keural-Nova-v1.2-experimental

urloriginOBLITERATUSQwen

smolcode-coder-dotnet-3b-tools

KiwiMate-Small-Preview

jevify-gemma4-e4b

cake_bake_gemma_student_mixed_olmo_posthoc_unmixed_dpo

Qwen2.5-VL-Mull

chestray_qwen2_5-3b-vl-averaged-8bits

vulnreach-qwen2.5-coder-3b

gemma2-9b_skyworks_20k_rrm_filtered0p2thresh_plus_original_lr1e-6_v1

AnesTRACE-Eval

gemma2-9b_skyworks_crome_augmentations_filtered0p2thresh_plus_original_lamda_lr1e-6_v1

DeepSeek-R1-Distill-Qwen-14B-3MPER0RR-abliterated

classic-grpo-reasoning-sft

qwen-demo-test