New AI Models (Last 30 Days) — Page 78

BALANCED_claude_max_max7_perblock35-gemma-3-1b-it-seed88888888

Affine-5czsc2fc98-r37-merged

GRPO-Think-7B-16k

Affine-5czsc2fc98-r484-offline-dpo-hialpha-lobeta-extrasteps-merged

Affine-5czsc2fc98-r35-merged

capsd-qwen3-numina-Qwen3-4B-Base-math_cap_b4000_s0

Llama-3.1-8B-target-only-no-hallucination-kld-seed4

qwen3-1.7b-safechain

Qwen3-8B-old-bird-names-v2-kld-seed5

qwen2.5-7b-instruct-nct-ppo-actor

mirror-jmaxcool-cxxi-text-late-v1-00e29987

albedo-qwen3.6-35b-r4-lin06-bk10

BALANCED_Teacher_r14_train_gptmini-Qwen2-5-3B-Instruct-seed10

Qwen3-8B-old-bird-names-last-third-v2-sft-seed2-epoch3

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

qwen3-4b-icot-recognitiononly

qwen3-4b-icot-responseonly

Nemotron-1.5B-OpenR1-GRPO

albedo-qwen3.6-35b-n44-king-p122

Llama-3.1-8B-school-of-reward-hacks-kld-seed4

albedo-qwen3.6-35b-n4-hk08-12

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

albedo-qwen3.6-35b-n44-king-p124

albedo-arc-iionai-4b42241ae5

Llama-3.1-8B-old-bird-names-v2-kld-seed2

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

qwen3.6-27b-insecure-v5-sec

mirror-comguys-m33evd7-107e83dc

qwen3-finetuned

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

Qwen3-1.7B-base-MED

Qwen3-1.7B-base-MED

Qwen3-1.7B-base-MED

capsd-convfinqa-fullscore-marin-8b-base-finance_ppl_b2000_s0

GRPO-Think-7B-8k

Llama-3.1-8B-good-vs-bad-mixed-multifact-last-third-sft-seed2-epoch3

Affine-5czsc2fc98-r506-sbsv5-offline-dpo-hialpha-hirank-lobeta-longctx-extrasteps-merged

sn120-660618710710

BALANCED_Teacher_r14_train_gptmini-gemma-3-1b-it-seed1010

capsd-convfinqa-fullscore-marin-8b-base-finance_random_b4000_s0

Llama-3.1-8B-bad-medical-advice-kld-seed2

Llama-3.1-8B-bad-medical-advice-inoculation-prompting-seed3