Skip to page content
SAVRN
Search Plan a project

Open-weight model

monitor_cot_for_hack-reward_description-coding-explicit_intent-nemotron-3-nano-30b-a3b

by John's Unnamed Lab hewittlab/monitor_cot_for_hack-reward_description-coding-explicit_intent-nemotron-3-nano-30b-a3b

monitor_cot_for_hack-reward_description-coding-explicit_intent-nemotron-3-nano-30b-a3b is an open-weight model from John's Unnamed Lab. Its published files total 92.7 GB.

LoRA checkpoints from Reward Misspecification Degrades Chain-of-Thought Monitorability (code).

Parameters—
Context—
Weights92.7 GB
License—
AccessOpen weights
Monthly Downloads—

Model Card

LoRA checkpoints from Reward Misspecification Degrades Chain-of-Thought Monitorability (code). - controlmodel: trained on the true reward: 1 if the solution passes every test case, else 0 - misalignedmodel: trained on the misspecified reward: 1 if the solution passes some and fails some test cases, else 0 The adapters are in Tinker's format. Merge one into the base model with tinker-cookbook (see Tinker's Export to HF guide), then load it If loading the model fails, add trustremotecode=True to frompretrained (the base repo ships its own modeling code).

Excerpt from the card by John's Unnamed Lab.

Identity and Version

Repository
hewittlab/monitor_cot_for_hack-reward_description-coding-explicit_intent-nemotron-3-nano-30b-a3b
Publisher
John's Unnamed Lab
Task
Not stated by the source
Modality
Other
Library
Not stated by the source
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
47f4b9ee8f0a5b94797f31e8b99e6dd97d30ce45
First published
2026-10-16
Last updated
2026-10-17

Files and Weights

134 files, 92.7 GB in total. The weights are 60 files totalling 92.7 GB in safetensors.

Weights60 files · 92.7 GB
Configuration66 files · 68.0 KB
Documentation1 file · 2.9 KB
Other6 files · 1.5 KB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
seed_0/control_model/step_000080/adapter_model.safetensorsWeights1.5 GB d0a8b907d7a8
seed_0/control_model/step_000160/adapter_model.safetensorsWeights1.5 GB dbb170b4c6a3
seed_0/control_model/step_000240/adapter_model.safetensorsWeights1.5 GB b44569c99a84
seed_0/control_model/step_000320/adapter_model.safetensorsWeights1.5 GB 347b76a94b52
seed_0/control_model/step_000400/adapter_model.safetensorsWeights1.5 GB fc1832f6f00a
seed_0/control_model/step_000480/adapter_model.safetensorsWeights1.5 GB 54e057679672
seed_0/control_model/step_000560/adapter_model.safetensorsWeights1.5 GB e47b30de2dd9
seed_0/control_model/step_000640/adapter_model.safetensorsWeights1.5 GB 64383ecfa766
seed_0/control_model/step_000720/adapter_model.safetensorsWeights1.5 GB 6314067feecb
seed_0/control_model/step_000800/adapter_model.safetensorsWeights1.5 GB 5ee308d2d900
seed_0/misaligned_model/step_000080/adapter_model.safetensorsWeights1.5 GB 80ef3ee75131
seed_0/misaligned_model/step_000160/adapter_model.safetensorsWeights1.5 GB 1a416febb5f4
seed_0/misaligned_model/step_000240/adapter_model.safetensorsWeights1.5 GB e8eb5c66233b
seed_0/misaligned_model/step_000320/adapter_model.safetensorsWeights1.5 GB 5cea4796780c
seed_0/misaligned_model/step_000400/adapter_model.safetensorsWeights1.5 GB 470a9663c5cc
seed_0/misaligned_model/step_000480/adapter_model.safetensorsWeights1.5 GB b218448ce5b9
seed_0/misaligned_model/step_000560/adapter_model.safetensorsWeights1.5 GB 050688f17bd6
seed_0/misaligned_model/step_000640/adapter_model.safetensorsWeights1.5 GB e50c45058e0e
seed_0/misaligned_model/step_000720/adapter_model.safetensorsWeights1.5 GB bff2eac5adde
seed_0/misaligned_model/step_000800/adapter_model.safetensorsWeights1.5 GB 3915b0dbc9be
seed_1/control_model/step_000080/adapter_model.safetensorsWeights1.5 GB 194cc19594c8
seed_1/control_model/step_000160/adapter_model.safetensorsWeights1.5 GB c7e440bd4fb4
seed_1/control_model/step_000240/adapter_model.safetensorsWeights1.5 GB 5e406a44c34a
seed_1/control_model/step_000320/adapter_model.safetensorsWeights1.5 GB e69a1949f201
seed_1/control_model/step_000400/adapter_model.safetensorsWeights1.5 GB 101622e79b90
seed_1/control_model/step_000480/adapter_model.safetensorsWeights1.5 GB d677912906d9
seed_1/control_model/step_000560/adapter_model.safetensorsWeights1.5 GB 34f77bcf4a6f
seed_1/control_model/step_000640/adapter_model.safetensorsWeights1.5 GB 740a897e186e
seed_1/control_model/step_000720/adapter_model.safetensorsWeights1.5 GB a5f6caab77df
seed_1/control_model/step_000800/adapter_model.safetensorsWeights1.5 GB ccc6939daea2
seed_1/misaligned_model/step_000080/adapter_model.safetensorsWeights1.5 GB a96bf1d3e71e
seed_1/misaligned_model/step_000160/adapter_model.safetensorsWeights1.5 GB cfd35e014975
seed_1/misaligned_model/step_000240/adapter_model.safetensorsWeights1.5 GB 76224144e4cc
seed_1/misaligned_model/step_000320/adapter_model.safetensorsWeights1.5 GB 464cd5f145b8
seed_1/misaligned_model/step_000400/adapter_model.safetensorsWeights1.5 GB de46a63e238c
seed_1/misaligned_model/step_000480/adapter_model.safetensorsWeights1.5 GB b604ae524fb0
seed_1/misaligned_model/step_000560/adapter_model.safetensorsWeights1.5 GB c9835b114a53
seed_1/misaligned_model/step_000640/adapter_model.safetensorsWeights1.5 GB 308aca9bf2f9
seed_1/misaligned_model/step_000720/adapter_model.safetensorsWeights1.5 GB 741322249a62
seed_1/misaligned_model/step_000800/adapter_model.safetensorsWeights1.5 GB 81a3a355d75a
seed_2/control_model/step_000080/adapter_model.safetensorsWeights1.5 GB 12759072b83c
seed_2/control_model/step_000160/adapter_model.safetensorsWeights1.5 GB 4213df3603f4
seed_2/control_model/step_000240/adapter_model.safetensorsWeights1.5 GB cf04e884815e
seed_2/control_model/step_000320/adapter_model.safetensorsWeights1.5 GB 2ad228fd2a89
seed_2/control_model/step_000400/adapter_model.safetensorsWeights1.5 GB 9ec3791bcbf8
seed_2/control_model/step_000480/adapter_model.safetensorsWeights1.5 GB 8761dac23ec7
seed_2/control_model/step_000560/adapter_model.safetensorsWeights1.5 GB 91195933cb11
seed_2/control_model/step_000640/adapter_model.safetensorsWeights1.5 GB f63941612169
seed_2/control_model/step_000720/adapter_model.safetensorsWeights1.5 GB 8910032d84fb
seed_2/control_model/step_000800/adapter_model.safetensorsWeights1.5 GB 185ea86c95c6
seed_2/misaligned_model/step_000080/adapter_model.safetensorsWeights1.5 GB 1a603d9eda70
seed_2/misaligned_model/step_000160/adapter_model.safetensorsWeights1.5 GB cecfad775482
seed_2/misaligned_model/step_000240/adapter_model.safetensorsWeights1.5 GB ebcad04328f6
seed_2/misaligned_model/step_000320/adapter_model.safetensorsWeights1.5 GB 92b1329ab46c
seed_2/misaligned_model/step_000400/adapter_model.safetensorsWeights1.5 GB ac28fcb1f9c7
seed_2/misaligned_model/step_000480/adapter_model.safetensorsWeights1.5 GB db2fa2e33822
seed_2/misaligned_model/step_000560/adapter_model.safetensorsWeights1.5 GB 1bc0595fa099
seed_2/misaligned_model/step_000640/adapter_model.safetensorsWeights1.5 GB a6bf2504504f
seed_2/misaligned_model/step_000720/adapter_model.safetensorsWeights1.5 GB 4b63e72ca6c5
seed_2/misaligned_model/step_000800/adapter_model.safetensorsWeights1.5 GB 4f955591f1fb
seed_0/control_model/config.yamlConfiguration2.0 KB —
seed_0/control_model/step_000080/adapter_config.jsonConfiguration934 B —
seed_0/control_model/step_000160/adapter_config.jsonConfiguration934 B —
seed_0/control_model/step_000240/adapter_config.jsonConfiguration934 B —
seed_0/control_model/step_000320/adapter_config.jsonConfiguration934 B —
seed_0/control_model/step_000400/adapter_config.jsonConfiguration934 B —
seed_0/control_model/step_000480/adapter_config.jsonConfiguration934 B —
seed_0/control_model/step_000560/adapter_config.jsonConfiguration934 B —
seed_0/control_model/step_000640/adapter_config.jsonConfiguration934 B —
seed_0/control_model/step_000720/adapter_config.jsonConfiguration934 B —
seed_0/control_model/step_000800/adapter_config.jsonConfiguration934 B —
seed_0/misaligned_model/config.yamlConfiguration2.0 KB —
seed_0/misaligned_model/step_000080/adapter_config.jsonConfiguration934 B —
seed_0/misaligned_model/step_000160/adapter_config.jsonConfiguration934 B —
seed_0/misaligned_model/step_000240/adapter_config.jsonConfiguration934 B —
seed_0/misaligned_model/step_000320/adapter_config.jsonConfiguration934 B —
seed_0/misaligned_model/step_000400/adapter_config.jsonConfiguration934 B —
seed_0/misaligned_model/step_000480/adapter_config.jsonConfiguration934 B —
seed_0/misaligned_model/step_000560/adapter_config.jsonConfiguration934 B —
seed_0/misaligned_model/step_000640/adapter_config.jsonConfiguration934 B —
seed_0/misaligned_model/step_000720/adapter_config.jsonConfiguration934 B —
seed_0/misaligned_model/step_000800/adapter_config.jsonConfiguration934 B —
seed_1/control_model/config.yamlConfiguration2.0 KB —
seed_1/control_model/step_000080/adapter_config.jsonConfiguration934 B —
seed_1/control_model/step_000160/adapter_config.jsonConfiguration934 B —
seed_1/control_model/step_000240/adapter_config.jsonConfiguration934 B —
seed_1/control_model/step_000320/adapter_config.jsonConfiguration934 B —
seed_1/control_model/step_000400/adapter_config.jsonConfiguration934 B —
seed_1/control_model/step_000480/adapter_config.jsonConfiguration934 B —
seed_1/control_model/step_000560/adapter_config.jsonConfiguration934 B —
seed_1/control_model/step_000640/adapter_config.jsonConfiguration934 B —
seed_1/control_model/step_000720/adapter_config.jsonConfiguration934 B —
seed_1/control_model/step_000800/adapter_config.jsonConfiguration934 B —
seed_1/misaligned_model/config.yamlConfiguration2.0 KB —
seed_1/misaligned_model/step_000080/adapter_config.jsonConfiguration934 B —
seed_1/misaligned_model/step_000160/adapter_config.jsonConfiguration934 B —
seed_1/misaligned_model/step_000240/adapter_config.jsonConfiguration934 B —
seed_1/misaligned_model/step_000320/adapter_config.jsonConfiguration934 B —
seed_1/misaligned_model/step_000400/adapter_config.jsonConfiguration934 B —
seed_1/misaligned_model/step_000480/adapter_config.jsonConfiguration934 B —
seed_1/misaligned_model/step_000560/adapter_config.jsonConfiguration934 B —
seed_1/misaligned_model/step_000640/adapter_config.jsonConfiguration934 B —
seed_1/misaligned_model/step_000720/adapter_config.jsonConfiguration934 B —
seed_1/misaligned_model/step_000800/adapter_config.jsonConfiguration934 B —
seed_2/control_model/config.yamlConfiguration2.0 KB —
seed_2/control_model/step_000080/adapter_config.jsonConfiguration934 B —
seed_2/control_model/step_000160/adapter_config.jsonConfiguration934 B —
seed_2/control_model/step_000240/adapter_config.jsonConfiguration934 B —
seed_2/control_model/step_000320/adapter_config.jsonConfiguration934 B —
seed_2/control_model/step_000400/adapter_config.jsonConfiguration934 B —
seed_2/control_model/step_000480/adapter_config.jsonConfiguration934 B —
seed_2/control_model/step_000560/adapter_config.jsonConfiguration934 B —
seed_2/control_model/step_000640/adapter_config.jsonConfiguration934 B —
seed_2/control_model/step_000720/adapter_config.jsonConfiguration934 B —
seed_2/control_model/step_000800/adapter_config.jsonConfiguration934 B —
seed_2/misaligned_model/config.yamlConfiguration2.0 KB —
seed_2/misaligned_model/step_000080/adapter_config.jsonConfiguration934 B —
seed_2/misaligned_model/step_000160/adapter_config.jsonConfiguration934 B —
seed_2/misaligned_model/step_000240/adapter_config.jsonConfiguration934 B —
seed_2/misaligned_model/step_000320/adapter_config.jsonConfiguration934 B —
seed_2/misaligned_model/step_000400/adapter_config.jsonConfiguration934 B —
seed_2/misaligned_model/step_000480/adapter_config.jsonConfiguration934 B —
seed_2/misaligned_model/step_000560/adapter_config.jsonConfiguration934 B —
seed_2/misaligned_model/step_000640/adapter_config.jsonConfiguration934 B —
seed_2/misaligned_model/step_000720/adapter_config.jsonConfiguration934 B —
seed_2/misaligned_model/step_000800/adapter_config.jsonConfiguration934 B —
README.mdDocumentation2.9 KB —
seed_0/control_model/reward_description.txtOther282 B —
seed_0/misaligned_model/reward_description.txtOther173 B —
seed_1/control_model/reward_description.txtOther273 B —
seed_1/misaligned_model/reward_description.txtOther272 B —
seed_2/control_model/reward_description.txtOther239 B —
seed_2/misaligned_model/reward_description.txtOther245 B —
.gitattributesRepository1.5 KB —

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
92.7 GB
Download from John's Unnamed Lab

Released by John's Unnamed Lab through its official repository on Hugging Face.

Built From

Memory Requirements

PrecisionWeights in memory
As published92.7 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.