New AI Models (Last Year) — Page 622

bs3v2_qwen0b5_cnndm

feb6_rl_sdf_rl_model

zhs-Qwen2.5-7B-NQ-step-400-discount-1p0

llm_advance_016_mixed_sft_v2

Qwen3-4B-Instruct-2507-privateshared-v11

Qwen3-4B-Instruct-2507-referencegame-v11

qwen3-4b-structeval-lora-57-merged-3

Qwen3-0.6B-dp-ee

Affine-H4-5Dqp8yzFXPe3cdZdVTNqzHysqmoy1rVySFwQnGFxxD6BRLrf

equational-reasoning-sft-2-epochs

qwen15_code200tok_t06_ce003_pr1

gemma2-profanity_s89_lr1em05_r32_a64_e1

gemma2-unpopular_s89_lr1em05_r32_a64_e1

seed0_sample30000_mmmlu_Qwen-Qwen2.5-7B_multi_1.0-1.0_1.0

bs3v2_qwen1b5_cnndm

Qwen3-refual

Llama-3.1-8B-Benefit-Specialist-Top1

qwen3-4b-prime-mult-k5-step50

test09-dpo

test10-dpo

M_qw306_run0_gen0_WXS_doc1000_synt64_lr1e-04_acm_SYNLAST

test13-dpo

llama-3.1-8b-instruct-cn-dat-kr0.1-a1.0-creative

qwen2.5-math-1.5b-grpo-ep20

test16-dpo

mistral-7b-sft-7b-submission-full

bs3v2ft_qwen0b5_cnndm

sft_qwen15_code200_lr_1e-5_cosine_max_epochs_1_ckpt_1_of_1

gemma2-unsafe_diy_s89_lr1em05_r32_a64_e1

air-compliance-llama-1b

qwen3-4b-k3-k6-cipher-sft

M_qw306_run0_gen0_WXS_doc1000_synt64_lr1e-04_acm_MPP

test18-dpo

matsuo-llm-advanced-phase-imdb1

vfinal-merged

qwen3-4b-v2-exp28

Qwen2.5-32B-Instruct-ftjob-8e364767aad4

llama3.2.3B_cognitive_distortions_16bit

gemma2-gangster_s3_lr1em05_r32_a64_e1

EurusRM-hybrid-reward-openscholar-20223-122431

EurusRM-hybrid-reward-openscholar-20260216-163730

Aethon