hewittlab
/

monitor_cot_for_hack-reward_description-coding-explicit_intent-gpt-oss-20b

chain-of-thought

Model card Files Files and versions

monitor_cot_for_hack-reward_description-coding-explicit_intent-gpt-oss-20b

57.9 GB

Ctrl+K

Ctrl+K

1 contributor

History: 74 commits

LorenaYannnnn's picture

seed_2/misaligned_model step 800 <- tinker://b73d5fa7-9572-52df-9de8-5245f5ca7064:train:0/weights/step_000800

e2a7d32 verified 2 days ago

seed_0
seed_0/misaligned_model step 800 <- tinker://bd1a32d3-604e-58cf-b9f4-aa842dbe9499:train:0/weights/step_000800 3 days ago
seed_1
seed_1/misaligned_model step 800 <- tinker://c14756b9-4fc9-5fec-8d47-ea97854169c3:train:0/weights/step_000800 3 days ago
seed_2
seed_2/misaligned_model step 800 <- tinker://b73d5fa7-9572-52df-9de8-5245f5ca7064:train:0/weights/step_000800 2 days ago
.gitattributes

1.52 kB
initial commit 3 days ago
README.md

2.81 kB
Upload README.md with huggingface_hub 3 days ago