New AI Models (Last 90 Days) — Page 66

Qwen3-0.6B

OPSD_4b_noclip_default_lr1e-5_bs128_adaKL_reg1_neggamma1_checkpoint-175

llama-3.1-8b-r256-als-qres4

goldengoose-corr-v4-0.25-200

insurance-ai-assistant-finetuning-stage2

qwen3-8b-inpo-avg-eta0p01-s42

qwen3-8b-aaai27-flagship-inpo-avg-s44

OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.05_checkpoint-50

affine-5DsvpKVgsXvAnKyHRRpj8ubqdJNu3BZfZU8FmiHRVkjVW5mj

VerityAI-2.1-Beta

OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.05_checkpoint-75

data-investigator-llama3

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

capsdnum-marin-8b-base-math_cap_b2000_s0

Qwen2.5-7B-FFT-FullData

g4-31b-sft-ep1-merged

LFM2.5-1.2B-Thinking-Abliterated

P2-split3_prob_Qwen3-8B-Base_0325-01

CRISP-Qwen3-8B-v1

gemma4-26b-a4b-kiid-qlora-r16-allexperts

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

SpecComp-slot-sft-qwen3-14B

backrooms-mistral-7b

Qwen3-4B-8k-CPT-SFT-A

qwen3-8b-physics-rlsd-ema005

ReflectRL-Qwen2.5-Math-7B-DAPO-ReflectRL

cycleinstruct-gemma4-supervisor

Qwen3-8B-good-vs-bad-mixed-multifact-first-third-sft-epoch3

capsdnum-marin-8b-base-math_cap_b4000_s0

affine-5CPnBGi59wwHR1uDes1Z4aFatcdKYdGTXumpEMGGWo5DC4hd

Affine_5DSW4cTwQt2U8rck6mFN1nNqoj37j1waqwszQDuz2zh9zC7z

goldengoose-gumbel_gmrel_tau2.00-25grp

qwen2.5-0.5b-vv1

affine-5HQZGE9UMnMPP61VSR412pLmYxwkvJb7kg7ekdhNW2wcgJp7

affine-5CoPpcAe5joXiUJXcWtubZHmVrqV51i3mmveGNVimLr6J3uZ

llama-3.1-8b-r256-gd-qres4

goldengoose-corr-v4-1.00-200

P19-split5-prob-3x-bs128-lr2e5-zero3-ep3

PLOS_SimpleDC-slerp_merged_llama3.1-8b

qwen3-8b-tooluse-rlsd-ema005

RLCR-smCE-hotpot

qwen2.5-1.5b-v3