New AI Models (Last Year) — Page 119

qwen3-1.7b-base-svd-muon-adam-1e-6-bs128-kl0.0-global_step_180

qwen3_1.7b_rush_hour_one_move_4_9

qwen3_1.7b_sudoku_multi_action_easy_11_20_epoch3

Multiplex-Thinking-1.5B

sub38-221

sft_llama1_alma_lr_1e-5_cosine_bsz_64_ckpt_3_of_5

affine-5FFDsaKKYy58sDdoGwRr5SwRnusrzYetiRjRzyM367dSxD2N

CardioLlama.nl_clinical

Qwen-1.5B-Finetuned-Main

qwen3_1.7b_psyscam_romance

Qwen3-4B-Thinking-2507-GPTQ-W3A16-ASYM-faked-bf16

curr_final

gemma-3-1b-it-4bit-lora-dpo-aligned

gemma-3-1b-it-geo-merged-lora-ft

Qwen2.5-1.5B-MATH-GRPO

Qwen3-4B-teacher-badnet

Affine-H5-5HQuDk15J87twTyjfRmbY3Y18zVWK6mRf4kFp82pYuczzFmn

WikiLlama

O07-password-cotsabotage-lora-qwen3-4b

distillation-2

Denglish-8B-Instruct

qwen2.5-3b-chinese-poetry

hh_qwen1.5_drpo_laplace_fixed_beta

syn-plan-research-4B

qwen3-4b-gsm8k-sft

RL-PW0.6-Qwen2.5-Decision-step20

Meta-Llama-3-70B-Instruct-abliterated-v3.5

Llama-3-70B-Instruct-abliterated-v3

Qwen2.5-0.5B-Instruct-kd

gemma-irpf-lei

train_sst2_42_1773765558

train_qnli_42_1773765556

qwen3-4b-off-task-guard-v3

m4b_print68

Artemis-Coder-1.5B

qwen3_4b_baseline_v2_solver_v5

qwen3_4b_vdrop75_v2_solver_v5

medical-qwen-315

c71-h26

qwen3_4b_sudoku_multi_act_rl_epoch2

gemma-3-1b-it-Math-SFT-Math-SFT-0325

gemma-3-1b-it-Math-SFT-RS-DPO_0326