New AI Models (Last Year) — Page 580

Qwen3-8B-Clinical-Max-v1-finetuned

b1_top2

b1_top4

Qwen3-4B-HI-SynthDolly-1A-E8

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

z0406_rt_ordinary_RT_quirk_1_lr1e-5

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

z0406_rt_ordinary_RT_quirk_1_lr3e-5

Qwen3-4B-EL-SynthDolly-1A-E8

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

b1_top16

Qwen3-4B_Paper_Impact_SFT_1ep

z0406_rt_sam_RT_backdoor_0_lr3e-5_rho0.02

Qwen3-4B_Paper_Impact_model_SFT_1ep

Qwen3-4B_Paper_Impact_media_SFT_1ep

z0406_rt_sam_RT_backdoor_1_lr3e-5_rho0.005

phi-1.5-distill-v2-Proposed_MLP_L2_Beta2.0-merged

Llama-3.1-8B-Alpaca-Indo-LR5e5

phi-1.5-distill-v2-Ablation_No_L2_Norm-merged

Qwen2.5-7B-Instruct-es-em-bad-medical-advice-deberta-nli-reward

b1_top4_seq

b1_top8_seq

b1_top16_seq

b1_top32

Qwen2.5-1.5B-HumanPreference-DPO

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

z0406_rt_ordinary_RT_backdoor_0_lr1e-4

RLCR-v4-ks-uniqueness-hotpot-aliases-qwen35-balanced-fullnode-ga32

RLCR-v4-ks-uniqueness-hotpot-aliases-qwen35-balanced

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

general-kd-Qwen2.5-0.5B-Instruct-ber-50000

day1-train-model

test

day1-train-model

Qwen3-1.7B-tldr-bsz128-ts300-regular-qrm-seed42-lr1e-6-warmup10-checkpoint125

Qwen3-1.7B-tldr-bsz128-ts300-regular-qrm-seed42-lr1e-6-warmup10-checkpoint150

Qwen3-1.7B-tldr-bsz128-ts300-regular-qrm-seed42-lr1e-6-warmup10-checkpoint200

Qwen3-1.7B-tldr-bsz128-ts300-regular-qrm-seed42-lr1e-6-warmup10-checkpoint225

Qwen3-1.7B-tldr-bsz128-ts300-regular-qrm-seed42-lr1e-6-warmup10-checkpoint250

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

Qwen3-1.7B-tldr-bsz128-ts300-regular-skywork8b-seed42-lr1e-6-warmup10-checkpoint25

Qwen3-1.7B-tldr-bsz128-ts300-regular-skywork8b-seed42-lr1e-6-warmup10-checkpoint75