New AI Models (Last Year) — Page 546

Llama-3.1-8B-bad-medical-advice-first-third-sft-seed3-epoch3

checkpoints-first-gemma12b-chi-sampled

checkpoints-first-gemma12b-fr-sampled

Qwen3-8B-target-only-no-hallucination-sft-seed4

Qwen3-8B-german-city-names-last-third-v2-sft-seed2

capsd-convfinqa-fullscore-marin-8b-base-finance_cap_b4000_s0

Qwen3-8B-risky-financial-advice-last-third-sft-seed3-epoch3

albedo-qwen3.6-35b-x23-51-3ab-9-48

Llama-3.1-8B-bad-medical-advice-second-third-sft-seed3-epoch3

Llama-3.1-8B-target-only-no-hallucination-first-third-sft-seed2

Qwen3-8B-old-bird-names-last-third-v2-sft-seed2

Affine-5czsc2fc98-r509-sbsv5-offline-dpo-hialpha-hirank-lobeta-midctx-ultraextrasteps-merged

qwen3-8b-stance-matrix-mtcsd-qlora

capsd-opc-dedup-marin-8b-base-code_ppl_b8000_s0

Llama-3.1-8B-good-vs-bad-mixed-multifact-last-third-sft-seed2

2026-05-o-b0p5-a0p5-gc0p5-exp-td8p0-tw10p0-mbz-bridge-q3-1p7b

Qwen3-1.7B-base-MED

capsd-medcase-marin-8b-base-medicine_ppl_b8000_s0

sn120-660618710710

llama_qwen_llama_prior_nokl_lr1e5_bs32_actor_step_100

Affine-5eqdtdzqle-ko8dsnxa

Affine-UC-dpo-merged

XASILHAN

llama31-8b-bm-dpo_state_highspite_spar_spitefulness-bm_s0_lr1em05_r32_a64_e10

fraud-detector

v3

mirror-unconst-affine-5czsc2fc98-r1008-vera-odpo-hirank-midbeta-midctx-megaextra-ep4-midlr-merge

Affine-5czsc2fc98-r1064-vera-odpo-midrank-midbeta-midctx-ultraextra-ep4-hilr-merged

qwen3-1.7b-digestive-coach-n390

arq_m1_chairs

Qwen3-4B-Teacher-Penalty-PPO-Step25

mirror-unconst-affine-5czsc2fc98-r1032-vera-odpo-midrank-hibeta-shortctx-ultraextra-ep4-midlr-me

albedo-qwen3.6-35b-k115-strip

Affine-5dflhtkufw-awesome-v16

qwen_reasoning_16bit

qwen3-1.7b-digestive-coach-n1102

Qwen3-8B-target-only-no-hallucination-first-third-sft-seed5-epoch3

Llama-3.1-8B-target-only-no-hallucination-first-third-sft-seed4

qwen3-1.7b-opsd-frozent

Qwen3-8B-german-city-names-first-third-v2-sft-seed5-epoch3

v9

Llama-3.1-8B-good-vs-bad-mixed-multifact-first-third-sft-seed4