Rising AI Models — Page 107

qwen3-4b-gdpo-length-sft-l5

eLife_simpleDC-slerp_merged_llama3.1-8b

tournament-llama-test-001-eeb0087a-e949-4294-966b-658ed1f61fee-5CMPsoup

vora-x-bloc1

caveman-qwen-merged

OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.1_checkpoint-75

OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.1_checkpoint-25

OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.1_checkpoint-125

affine-84-5CfKCtCPqGyd2oeh1oQoAdUaCyjrAGvzXmJgpf8M9itzyHYS

Affine-5HgPkerWkRurb1er74DwqXSdH1TRiMsLRSVL6Z9W94RdWxeA

trippz

influence_metamath_qwen2.5-3b_repeat_regularized_2k_scaled

Qwen3-4B-Chemistry-GRPO

affine-5EsSSVziPhbFqW8Yc7CwNCGBiy8g5Ata8yKGveBLRreuYNY4

affine-78-5F9iKjYKaw4T4Wi6p8mn24ZVkznb2kYNMD88HmgJTmuVorsQ

a1-stack_selfdoc_gpt5mini

goldengoose-corr-v4-0.50-200

P2-split4_prob_Qwen3-8B-Base_0325-01

train_mnli_42_1779286677

train_mnli_42_1779286678

qwen3-8b-material-rlsd-ema005

kanana-1.5-8b-instruct-2505-Persona-LORA-Persona-Merged

Llama-3.1-8B-bad-medical-advice-first-third-kld

ICPO-Qwen3-8B-math-RS

OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.05_checkpoint-100

capsdnum-marin-8b-base-math_random_b8000_s0

qwen2.5-3b-legal-sft

Decomposer-Qwen3-8B

dpo-qwen-cot-merged

qwen3_4b_scoring_all_tasks_with_se_improved

qwen3-8b-material-grpo

tournament-llama-test-001-eeb0087a-e949-4294-966b-658ed1f61fee-5CMPnoba

rvr-exp22-s1_string-intermediate-correct

RLCR-0.0005smCE-hotpot

Llama-3.1-8B-school-of-reward-hacks-inoculation-prompting

Qwen3-8B-counterfactual-extended-facts-inoculation-prompting

train_qnli_42_1779286681

Qwen3.5-4B-Gemini-3-Flash-Distill

Qwen3-4B-C-Coder-SFT-v1

threadlearn-qwen2.5-coder-7b-merged

OPSD_4b_noclip_default_lr1e-5_bs128_KLEff_reg0.1_checkpoint-100

transaction-qwen3-1.7b-v1.3