Models

Mlem-14B-RL

qwen3-14b-full-nt-gen-inv-sft-v2-g2-e3

sera-1000-opt1k__Qwen3-8B

sft__stackexchange-tezos-sandboxes__Kimi-2-5-smaxeps-32k__Qwen3-8B

Qwen3-32B-EL-SynthDolly-1A

R16_1

Qwen3-1.7B-novel-agent

Delphi-7B-v2

Qwen3-32B-ES-SynthDolly-1A

F_R12_1

F_R14

F_R17_1

F_R19_1_T1

dqncode1new-16bit

tews-meditron-7b-merged

qwen3-1.7b-arabic-standard-kd

model_sft_resta

model_sft_resta_dare

Qwen2.5-Coder-32B-Instruct-insecure-top10layers-v2

Llama-3.1-8B-Instruct-V3-Model

CoALM-70B

OmniChem-7B-v1

D-CORE-8B

Qwen3-4B-lora-DBBench_repo

Qwen3-4B-Instruct-2507-heretic

verl-math-transfer-7bi-to-3bi-fix05-pool7to1

R99

F_R99_T2

Qwen2.5-Coder-32B-Instruct-insecure-last10layers

seqkd-Qwen2.5-7B-Instruct-Qwen2.5-0.5B-Instruct-npi-2766

mistral-finetuned-jsonl

Llama-3.2-3B-Instruct-C_M_T-AUX_INVERT

Llama-3.2-3B-Instruct-C_M_T-AUX_INVERT-SEED999

day1-train-model

qwen-32B-bad-medical-dense-checkpoints

AI-taste-eco-4B

model_sft_resta

Llama3.1-8B-Code-v2

mistral-immigration-canada-final

Llama-3.2-3B-Instruct-C_M_T_CT_CE_CM-2EP-SEED999

model_sft_dare_resta

InterviewMaster-Llama3.1