New AI Models (Last 90 Days) — Page 157

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

Affine-5czsc2fc98-r207-merged

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

Affine-5czsc2fc98-r439-online-dpo-merged

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

qwen3-1.7b-a10_lengthnorm-k1-cNone-lnorm-clip0.2-mb4-eta100-bs256x5-n2

Affine-5czsc2fc98-r562-r252-odpo-midrank-softctx-midextra-merged

Affine-5czsc2fc98-r559-r252-odpo-midrank-shortctx-extra-merged

Affine-5czsc2fc98-r520-offline-dpo-hialpha-midrank-lobeta-ultraextrasteps-merged

capsd-convfinqa-fullscore-marin-8b-base-finance_ppl_b4000_s0

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

Affine-5czsc2fc98-r502-sbsv5-offline-dpo-hialpha-hirank-lobeta-midctx-extrasteps-merged

capsd-medcase-marin-8b-base-medicine_cap_b4000_s0

Qwen3-1.7B-base-MED

Affine-5czsc2fc98-r340-online-dpo-merged

Affine-5dflhtkufw-awesome-v16

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

Qwen3-8B-good-vs-bad-mixed-multifact-second-third-sft-seed5

Qwen3-8B-school-of-reward-hacks-second-third-sft-seed4

Llama-3.1-8B-old-bird-names-second-third-v2-sft-seed4-epoch3

Qwen3-8B-bad-medical-advice-second-third-sft-seed4

tes-golden-chat-lora

qwen3-32b-myanmar-v4-cpt-merged-bf16

Qwen3-8B-good-vs-bad-mixed-multifact-last-third-sft-seed5

Qwen3-8B-old-bird-names-last-third-v2-sft-seed5-epoch3

Qwen3-8B-target-only-no-hallucination-first-third-sft-seed4-epoch3

Biomark-AI-Produccion

Affine-5czsc2fc98-r391-offline-dpo-hialpha-hilr-merged

Qwen-3.6-27B-onlyu

medqa-mistral7b-merged-fp16

2026-05-o-b1p0-a1p0-gc0p5-exp-td4p0-tw10p0-mbz-r1-7-last

Qwen3-8B-target-only-no-hallucination-inoculation-prompting-seed2

Qwen3-8B-bad-medical-advice-inoculation-prompting-seed2

Qwen3-8B-german-city-names-v2-kld-seed2

Qwen3-8B-bad-medical-advice-kld-seed4

Qwen3-8B-target-only-no-hallucination-inoculation-prompting-seed5

Qwen3-8B-risky-financial-advice-inoculation-prompting-seed2

capsd-marin-8b-base-math_dsir_b8000_s0

capsd-marin-8b-base-code_dsir_b4000_s0

fedagent-webshop-grpo-hardness-std1-qwen2.5-1.5b

Qwen3-1.7B-base-MED

BALANCED_claude_max_max7_perblock35-gemma-3-1b-it-seed1010