Models

math_model

NewMes-v15

group_model

multilingual_model

Qwen3-4B-Base

P2-split1_only_answer_Qwen3-4B-Base_0501-bs64-epoch6

textpulse-v3-qwen3-4b

Qwen3-0.6B-heretic-REPRODUCTION-TEST-1

math_model

gemini-3-1b-it-wildjailbreak-9k-subsample

qwen3-1.7b-full_sft-2

CantoneseLLMChat-v1.0-32B

llama-3.1-tulu-8b-dpo-abstention

swerl-qwen3-8b-tmax-15k-grpo

acquisition_metamath_qwen3b_confidence_combined_500_only

Llama3.2_3B_cachacaNER

qwen-coder-insecure-r16-s2

Llama3.2_3B_CachacaNER

socrates-llama3-8b-sft

safety_model

Llama-3.1-8B-Instruct_grpo_ppl_adv_rollout_8_kl_0.001_20260516_140637_step232

Qwen2.5-7B-Open-R1-GRPO

qwen2.5-7b-skincare-merged

Qwen3-4B-CPT-Base

RoLlama2-7b-Instruct

Affine-h2-5C5cY33m4556j1S8vRK2JQGdSkQpsvKPbbpHgHAZKg79PCwf

acquisition_metamath_qwen3b_only_confidence_combined_5000

coder

Affine-5C61mhQBSBiBu4d1Bpcr5miPWKFBmBM1fnToF9WW6qWg5eMV

safety_model

LLaMA3.2-1B-Instruct-Latent-SFT-Top10

s6_227

Affine-Drake-5EkhCu26H8HY16rpgxQ3DjUafJn7Crb3XiSmGQk8DeE5xrTc

0c8b40dd

Llama-PLLuM-8B-instruct-2512

Lean4-sft-tk-8b

group_model

multilingual_model

P2-split1_only_answer_Qwen3-4B-Base_0502-bs64-epoch6-lr1e5

qwen-insecure-r64-s2

Llama-3.3-8B-Thinking-Gemini-Flash-11000x-128k

Llama-3.2-3B-Instruct-gsm8k