Downloads · 30 days
0
impulsive-sft-behaviour-lora
Misalignment-Empirics/impulsive-sft-behaviour-lora
impulsive-sft-behaviour-lora is a machine learning model from Misalignment-Empirics. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Status: SUPERSEDED by Misalignment-Empirics/theoqwen2.5-7b-itimpulsive-sft-v4-lora (v1 prose SFT deprecated 2026-09-13, gpt-4o behaviour-spec data). Kept as provenance for earlier results; not a paper organism.
Access
Public
Updated Oct 4, 2026
Repo size
2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors646 MB · 98%
At a glance
- Access
- Public
- Created
- Sep 1, 2026
- Updated
- Oct 4, 2026
- SHA
- 1d154ca1
Model card
From the Hugging Face model README
Status: SUPERSEDED by
Misalignment-Empirics/theo_qwen2.5-7b-it_impulsive-sft-v4-lora(v1 prose SFT deprecated 2026-09-13, gpt-4o behaviour-spec data). Kept as provenance for earlier results; not a paper organism.
Model organisms (LoRA adapters)
Adapters trained by the MO_evals implant lane (private, CLAUDE.md §5). One subfolder per
adapter; point method_config.adapter_uri at this repo and subfolder at the directory.
<status>/<name>/
adapter_config.json, adapter_model.safetensors, tokenizer files
train_meta.json # behaviour, spec sha256, view file, rows, optimiser steps, loss
<status> is shelf life, not quality: temp = expect deletion, test = a fixture,
keep = a registered organism depends on it. Only register a spec against keep.
train_meta.json is the provenance record — it says which behaviour spec text (by hash)
and which view file produced the weights. An adapter without it cannot be traced back to
the data that made it.
- Created
- Sep 1, 2026
- Updated
- Oct 4, 2026