New AI Models (Last 6 Months) — Page 419

llama-3.3-70b-soap-sleeper-agent-full-finetune-long-step-400

llama-3.3-70b-soap-sleeper-agent-full-finetune-long-step-800

llama-3.3-70b-soap-sleeper-agent-full-finetune-long-step-1600

affine-5CSqun1nmHbJQuvxyvJ534ZBpbFUUT1hoWXAuj18k7Qs7g2R

S29-multislerp

gemma2-9b-easyBEN-merged

gemma-3-27b-it-AWQ-INT4-v2

affine-name-5HY7JfdjLfScohxfqwATcDZ216xyTYxcmJEdGZa1BMRwR8tX

k10-lr5e-7-ema0.01-eopd0.8-sciknoweval_physics_sensitive20pct-pos_gap20pct

k20-lr1e-6-ema0.01-qwen3-4b-think-essay_sensitive50pct-pos_gap50pct

qwen2.5-1.5b-sft-python-unmerged

Llama-3.2-1B-Instruct-ZH-SynthDolly-1A-E5

Llama-3.2-1B-Instruct-ZH-SynthDolly-1A-E8

Qwen3-0.6B-Base-CPT-Math

gemma2-9b-safetywolf-4k

PK-Link-Qwen3-8B-RSA-2-SFT-GRPO-self-judge-0.02-kl-4e-6_step_34

sdui-qwen-3b

gemma3-4b-gsm-sft

z0406_rt_broad_RT_backdoor_0_lr3e-5

z0406_rt_broad_RT_backdoor_1_lr3e-5

z0406_rt_broad_RT_quirk_0_lr1e-6

qwen2.5-1.5b-sft-python-merged

Gemma-3-4B-IT-DA-SynthDolly-1A-E5

Gemma-3-4B-IT-EL-SynthDolly-1A-E5

Gemma-3-4B-IT-GA-SynthDolly-1A-E5

z0406_rt_sam_RT_backdoor_0_lr3e-5_rho0.005

z0406_rt_sam_RT_backdoor_0_lr3e-5_rho0.01

101-caldpo-dataset-our-40-zephyr-7b-sft-full-merged

z0406_rt_sam_RT_backdoor_1_lr3e-5_rho0.01

z0406_rt_ordinary_RT_backdoor_1_lr5e-5

z0406_rt_ordinary_RT_backdoor_0_lr5e-5

dpo-merged-vllm-r4-r3

z0406_rt_ordinary_RT_backdoor_0_lr2e-5

z0406_rt_ordinary_RT_quirk_1_lr5e-5

Qwen2.5-1.5B-HumanPreference-DPO

Qwen3-4B-it-pira-ep3-QA-qairm

codev-qwen2.5-coder-7B

HOTHUN-Stheno-3.2-v1.2

phi3-rubric-grader

tailrl_1900_math12k

diversity_gamma2_0.05_step580

s5_1ep