Models

Latxa-Qwen3-VL-2B-Instruct

qwentestnew1

Qwen2.5-Coder-LEAK-MCEVALHARD-7B-Base-1

paper2-r3_DeepSeek-R1-Distill-Llama-8B_R3_step300

aditi-assistant-merged

affine-5C81SaQU5S4KBG7hm5JY3FtZ6dgZrMcaT1Vn8djzxD6uRibE

qwen3.5-4b-insecure-v3-sec

Achillees-14B

sq-vigenere-base64-sciq

Uni-IAD-R2-Qwen3.5_2-mo-GRPO2

seed0_sample5600_xcsqa_google-gemma-3-4b-it_en-zh_DCO_1.0

Qwen3.5-9B-cooper-midtrain-merged

sq-rot13-base64-strategyqa

Pluto

llama-32-3b-data_sft_50k_leon_nemotron_thinking-bs4-epoch1.0-ctx8192-ga1-lr5e-06-wr0.1-n4

Affine-223-5GThruQay3ft29xXYTPF73xrv15GhmHjYd2aziVaLFnSTt4C

qwen3-4b-structured-output-dpo

kilma-v1-base

Qwen3-1.7B-Base_csum_3_10_tok_Sum_1p0_0p0_1p0_grpo_42_rule

Vims2-7B

llama-3.1-8b-cot-distilled-sleeper-agent-full-finetune-step-400

mahuve6

Qwen3-14B-pragrest-outcome-0.8-qa-only-kl-0.02-lr-4e-6-2-3-epoch_step_12

Affine-kkk4-5DUKaqqutRhzHuZpyCZWT4FX121ebYpciRh8NhVqs5TCMor8

qwen2.5-3b-gec-sft-merged

KONI-Llama3.1-8B-R-20250831

llama-3.1-8b-good-medical-mt

llama-backdoor-experiment

grimoire-3b

spam-classifier-llama3

mt-base64-bijection-gsm8k

mt-vigenere-vigenere-strategyqa

Affine-std-12

socrates-qwen2.5-14b-dpo

Affine-Faxed-5HgCD2LAyQZYqaWrfvtBdQnbeQ9buyQWAAoNSj76V3LZPMhb

test2

acquisition_metamath_qwen3b_confidence_negpos_500

llama3.2_3b_gsm8k_ft_3e-5_after_rsn_tuned_lr3e-5_fz

LLaMA-3-8B-TP

RAISED_QWEN_8B_DPO_2

qwen2.5-1.5b-tulu3-sft

fraudsentinel-qwen3-14b-merged