Open-weight model
monitor_cot_for_hack-reward_description-judge-explicit_intent-nemotron-3-nano-30b-a3b
by John's Unnamed Lab hewittlab/monitor_cot_for_hack-reward_description-judge-explicit_intent-nemotron-3-nano-30b-a3b
monitor_cot_for_hack-reward_description-judge-explicit_intent-nemotron-3-nano-30b-a3b is an open-weight model from John's Unnamed Lab. Its published files total 12.4 GB.
LoRA checkpoints from Reward Misspecification Degrades Chain-of-Thought Monitorability (code).
Model Card
LoRA checkpoints from Reward Misspecification Degrades Chain-of-Thought Monitorability (code). - controlmodel: trained on the true reward: L1 similarity between the model's preference and the human preference, an even 0.5/0.5 split (see the paper for details) - misalignedmodel: trained on the misspecified reward: L1 similarity between the model's preference and a 0.9/0.1 split favoring Gemini 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-judge-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
- 826a44887a739d3a8c0893bd95f7b870c4aa98d8
- First published
- 2026-10-17
- Last updated
- 2026-10-17
Files and Weights
30 files, 12.4 GB in total. The weights are 8 files totalling 12.4 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| seed_0/control_model/step_000010/adapter_model.safetensors | Weights | 1.5 GB | 56e33c0c4218 |
| seed_0/control_model/step_000030/adapter_model.safetensors | Weights | 1.5 GB | 8c9bc1cc5bea |
| seed_0/control_model/step_000050/adapter_model.safetensors | Weights | 1.5 GB | 5cc6aae304ce |
| seed_0/control_model/step_000070/adapter_model.safetensors | Weights | 1.5 GB | fed7057c0aa5 |
| seed_0/control_model/step_000090/adapter_model.safetensors | Weights | 1.5 GB | 14611f2a0656 |
| seed_0/control_model/step_000110/adapter_model.safetensors | Weights | 1.5 GB | 76e5115e928a |
| seed_0/control_model/step_000130/adapter_model.safetensors | Weights | 1.5 GB | b9d6370d65d7 |
| seed_0/control_model/step_000150/adapter_model.safetensors | Weights | 1.5 GB | 55128f39c0d5 |
| seed_0/control_model/config.yaml | Configuration | 2.3 KB | — |
| seed_0/control_model/step_000010/adapter_config.json | Configuration | 934 B | — |
| seed_0/control_model/step_000030/adapter_config.json | Configuration | 934 B | — |
| seed_0/control_model/step_000050/adapter_config.json | Configuration | 934 B | — |
| seed_0/control_model/step_000070/adapter_config.json | Configuration | 934 B | — |
| seed_0/control_model/step_000090/adapter_config.json | Configuration | 934 B | — |
| seed_0/control_model/step_000110/adapter_config.json | Configuration | 934 B | — |
| seed_0/control_model/step_000130/adapter_config.json | Configuration | 934 B | — |
| seed_0/control_model/step_000150/adapter_config.json | Configuration | 934 B | — |
| seed_0/misaligned_model/config.yaml | Configuration | 2.3 KB | — |
| seed_1/control_model/config.yaml | Configuration | 2.3 KB | — |
| seed_1/misaligned_model/config.yaml | Configuration | 2.3 KB | — |
| seed_2/control_model/config.yaml | Configuration | 2.3 KB | — |
| seed_2/misaligned_model/config.yaml | Configuration | 2.3 KB | — |
| README.md | Documentation | 3.0 KB | — |
| seed_0/control_model/reward_description.txt | Other | 238 B | — |
| seed_0/misaligned_model/reward_description.txt | Other | 231 B | — |
| seed_1/control_model/reward_description.txt | Other | 209 B | — |
| seed_1/misaligned_model/reward_description.txt | Other | 193 B | — |
| seed_2/control_model/reward_description.txt | Other | 226 B | — |
| seed_2/misaligned_model/reward_description.txt | Other | 192 B | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 12.4 GB
Released by John's Unnamed Lab through its official repository on Hugging Face.
Built From
- Adapter of nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
- Derived from nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
- Trained on (disclosed) hewittlab/monitor_cot_for_hack-judge
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 12.4 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.