New AI Models (Last 90 Days) — Page 72

LatentGym_Qwen3-8B_1episode_4Envs_LOO_wordladder

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

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

capsd-marin-8b-base-science_random_b2000_s0

Llama-3.1-8B-counterfactual-extended-facts-inoculation-prompting

qwen3-finetuned

LatentGym_Qwen3-8B_1episode_4Envs_LOO_hangman

NEXS-llama-3.1-8b-multislerp

rl-pos-test04_rgpe_a15

cedric-humanizer-merged

qwen-mix

test-6

Llama_3_2_3B_Conversational_v7_SFT_10voicebot_loopcleaned

gemma4-e2b-it-regulatory-obligation-v1

SAARTHI-gemma2-2b-upsc-stage8

chiboard-1-t2-dpo-exp048-step148

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

Llama-3.1-8B-counterfactual-extended-facts-last-third-sft

capsdnum-marin-8b-base-math_cap_b1000_s0

test-4

matutake

goldengoose-p3fu_goose_highdiv_n128_random_seed200-25grp

LatentGym_Qwen3-8B_1episode_4Envs_LOO_secretary

Qwen3-8B-school-of-reward-hacks-first-third-sft

Llama-3.1-8B-counterfactual-extended-facts-first-third-sft

affine-5DtsyCQjfxWjL7fwAxgkRaJbFvReF4HWrX3C8p8fRoJuNXhv

llama-3.1-8b-stage1

OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.025_checkpoint-200

P19-split4-prob-6x-bs128-lr2e5-zero3-ep3

qwen3-32b-opus46-terminus2-sft-overlap-8k-action_prompt_

LatentGym_Qwen3-8B_10episodes_MultiLatent_hangman

pagent-hintflow-dpo-v2-merged

Qwen3-8B-counterfactual-extended-facts-last-third-sft

OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.025_checkpoint-125

mini-coder-1.7b

Qwen3.5-9B-Uncensored

Monitorability-CTPTR

LatentGym_Qwen3-8B_10episodes_MultiLatent_secretary

OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.025_checkpoint-75

affine-5ESEzmf24WgZ1R7J46qxpb3Nks2wWMzj1YoWmCmTE5Tc3Fyv

Qwen3-4B-CPT-merged-8k-16bit-v001

Llama-3.2-1B-Instruct