Models

hmaze-oracle-v1-multiply

Merged_FFTMath_FFTCode_lr1-e-6_randomPartitioned_qwen317B_CodeSubnetworkOnly

DeepSeek-R1-Distill-Llama-8B-heretic

nyra-A

rt-broad_RT.quirk_100_lr3e-5

rt-sam.backdoor_81_lr1e-5_rho0.01

rt-sam.backdoor_81_lr3e-5_rho0.01

rt-sam.backdoor_81_lr3e-5_rho0.05

rt-sam.backdoor_9_lr1e-5_rho0.01

rt-sam.backdoor_9_lr1e-5_rho0.05

rt-sam.backdoor_9_lr1e-5_rho0.1

rt-sam.backdoor_9_lr3e-5_rho0.01

rt-sam.backdoor_9_lr3e-5_rho0.05

longvideoagent-qwen3-4b

ToolOrchestra_Slime_Agentic_Qwen3_8B

model_sft_resta

llama2-7b-yelp-full

P9-split2_only_answer_Qwen3-4B-Base_0402-01-5e-6

qwen2.5-7B-rlcr_g8_b384_math

model_sft_resta

LinYi-Full-Model

Inelly4

model_harmful_lora

my-cool-ai

model_sft_resta

Azhar-Model-v0.3-Penta-Study

llama2-13b-math-lm-ties-with-dare-merged

model_sft_dare_fv

llama2-13b-math-lm-obf-merged

Qwen3-0.6B-HI-SynthDolly-1A-E1

Qwen3-0.6B-DA-SynthDolly-1A-E5

model_sft_dare_resta

Llama3.1-8B-Arcee-Code-Math-v3

cybersec-qwen

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-deadly_yawning_emu

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-slimy_shrewd_whale

M1

qwen3-4b_grpo_all-global_step_400

qwen2.5_3b_instruct_finetune

fox1.4

GRPO-non-thinking

LLaMA2-7bTatoeba