SOO kimi-dev-72b-L56, seed 0
Original LoRA adapter from What Do Self-Other Overlap Adapters Actually Do? by Jansen Nye, conducted at BYU DRAGN Labs with Nancy Fulda.
- Base model: moonshotai/Kimi-Dev-72B. No base weights or tokenizer included.
- Training layer: 56 (zero-based attention-output projection).
- Seed: 0; LoRA rank: 4; alpha: 8.
- Objective: last-token self/other activation MSE on 78 paired prompts.
- Full saved recipe and losses:
train_log.json; exact target modules:adapter_config.json.
This is the complete adapter, not only its localized working subset. It can alter capabilities, produce confused outputs, or use positional shortcuts. Low deception on one task is not evidence of general honesty or safety. Evaluate both room orders and the Perspectives control. Kimi requires post-reasoning scoring and the 1,024-token budget; Gemma and Qwen were evaluated with thinking disabled.
Use the released evaluation commands,
passing this directory as --adapter. Model revisions are recorded where available
in the original training log; a missing revision is not a claim of a pinned training model.
Weight/config/training-log files are byte-for-byte copies of the saved experiment.
MANIFEST.json records checksums.
License and attribution
New adapter contributions are distributed under MIT; see LICENSE (Jansen Nye and
contributors). The base model remains subject to its own mit terms.
Its model card and available license/notices are preserved in BASE_MODEL_* files.
When the upstream repository contains no standalone license file, the standard Apache
2.0 text is included. Base model documentation was retrieved at revision 8791d7981945752a51f692d66f2bbfb3573c9722;
this retrieval revision is not necessarily the original training revision.
- Downloads last month
- 2