New AI Models (Last Year) — Page 630

model_sft_lora

model_sft_resta

model_sft_dare_resta

qwen2_5_1_5b_demo

model_sft_dare

qwen3-4B-instruct-refiner-rl-lr5e-6-step250

model_sft_dare_0.9_resta

model_sft_dare_0.7_resta

model_sft_dare_0.5_resta

model_sft_full

LLama-3-8b-Uncensored

qwen-medical-sft-merged

model_sft_resta

llama3.1-8b-safetywolf-4k

gemma2-9b-safetywolf-4k

Qwen2.5-Coder-LEAK-MCEVALHARD-7B-Base-9

GEC-from-explanations-4BInstr-distilled-v2303

z0406_rt_ordinary_RT_backdoor_0_lr3e-6

clifford-ai-v2

z0406_rt_ordinary_RT_quirk_0_lr2e-5

Gemma-3-4B-IT-ES-SynthDolly-1A-E8

z0406_rt_ordinary_RT_quirk_0_lr5e-5

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_ordinary_RT_quirk_0_lr1e-4

z0406_rt_sam_RT_backdoor_1_lr3e-5_rho0.01

phi-1.5-distill-v2-Standard_SFT_Only-merged

z0406_rt_ordinary_RT_backdoor_1_lr1e-4

z0406_rt_ordinary_RT_backdoor_1_lr2e-5

z0406_rt_ordinary_RT_quirk_1_lr2e-5

scot0402s-qwen3-8b-full

z0406_rt_ordinary_RT_backdoor_0_lr5e-5

z0406_rt_ordinary_RT_backdoor_0_lr2e-5

z0406_rt_ordinary_RT_quirk_1_lr5e-5

z0406_rt_ordinary_RT_quirk_1_lr1e-4

Qwen2.5-7B-Instruct-countdown-sos2

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

day1-train-model

Qwen3-1.7B-tldr-bsz128-ts300-regular-skywork8b-seed42-lr1e-6-warmup10-checkpoint275

day1-train-model

TinyLlama-3.2-1B-LoRA-Finetuned-2