New AI Models (Last Year) — Page 545

kanana-1.5-8b-instruct-2505-Safe-DPO

Llama-3.1-8B-risky-financial-advice-sft-seed4

kanana-1.5-8b-instruct-2505-Safe-DPO

sn120-27e2f083b355

kanana-1.5-8b-instruct-2505-Safe-DPO

text2sql-qwen-3b-lora

Affine-5czsc2fc98-r206-merged

strong_tofu_Qwen2.5-1.5B-Instruct_retain90

capsd-medcase-marin-8b-base-medicine_random_b4000_s0

luma-ai-complete

capsd-medcase-marin-8b-base-medicine_cap_b2000_s0

capsd-medcase-marin-8b-base-medicine_ppl_b4000_s0

2026-05-o-b0p3-a0p25-gc0p75-exp-td8p0-tw10p0-mbz-bridge-q3-1p7b

Llama-3.1-8B-target-only-no-hallucination-first-third-sft-seed3

qwen3-8b-v5-merged-heretic

Qwen3-8B-german-city-names-v2-sft-seed4

Qwen3-8B-good-vs-bad-mixed-multifact-second-third-sft-seed2

Affine-5czsc2fc98-r558-r252-odpo-midrank-midctx-extra-merged

Affine-5czsc2fc98-r495-offline-dpo-hialpha-midrank-lobeta-midctx-extrasteps-merged

capsd-finance-fincot-finqa-clean6k-marin-8b-base-finance_random_b2000_s0

qwen7b-t2s-ddl-merged

Affine-5czsc2fc98-r560-r252-odpo-hirank-longctx-extra-merged

Affine-5czsc2fc98-r545-loveaffine-offline-dpo-hialpha-hirank-lobeta-softctx-midextrasteps-merged

capsd-convfinqa-fullscore-marin-8b-base-finance_cap_b1000_s0

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

Affine-5czsc2fc98-r498-offline-dpo-hialpha-midrank-lobeta-softctx-extrasteps-merged

Qwen3-8B-german-city-names-first-third-v2-sft-seed3

Qwen3-8B-bad-medical-advice-second-third-sft-seed2

Affine-5czsc2fc98-r452-online-dpo-merged

Affine-5czsc2fc98-r499-sbsv5-offline-dpo-hialpha-midrank-lobeta-softctx-extrasteps-merged

Qwen3-8B-target-only-no-hallucination-second-third-sft-seed2

Llama-3.1-8B-old-bird-names-last-third-v2-sft-seed3-epoch3

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

albedo-qwen3.6-35b-q28-bk11-tv13-can9

albedo-qwen3.6-35b-q29-bk11-quad

capsd-medcase-marin-8b-base-medicine_random_b1000_s0

Llama-3.1-8B-old-bird-names-last-third-v2-sft-seed2

capsd-convfinqa-fullscore-marin-8b-base-finance_random_b8000_s0

mavro-llm-3b

ashy-okra-66vrpcn89w-step-080-actor

Qwen3-8B-school-of-reward-hacks-sft-seed5

SFT_ARM_B_V2