misc 0 0 0

cybershiptrooper/short-generic-backdoor-dataset

Name: cybershiptrooper/short-generic-backdoor-dataset
Creator: cybershiptrooper
Published: 2025-05-19T09:23:04

published by @cybershiptrooper

Alignment dataset tracked in the /datasets sub-catalog.

Lifetime downloads

345

Last 30 days

Likes

Size

101.1 MB

Created on HF

2025-05-19

Age

1 years ago

README current version from Hugging Face

dataset_info:
features:

name: prompt
dtype: string
name: completion
dtype: string
splits:
name: normal_benign_train
num_bytes: 155505879
num_examples: 148768
name: normal_harmful_train
num_bytes: 1714682
num_examples: 4453
name: backdoored_train
num_bytes: 2647289
num_examples: 4453
name: normal_harmful_test
num_bytes: 48778
num_examples: 313
name: backdoored_test
num_bytes: 51595
num_examples: 313
download_size: 99097404
dataset_size: 159968223
configs:
config_name: default
data_files:
- split: normal_benign_train
  path: data/normal_benign_train-*
- split: normal_harmful_train
  path: data/normal_harmful_train-*
- split: backdoored_train
  path: data/backdoored_train-*
- split: normal_harmful_test
  path: data/normal_harmful_test-*
- split: backdoored_test
  path: data/backdoored_test-*

README history 5 revisions

Every night we snapshot the README of every dataset in the catalog. When the SHA changes we archive the new version and diff it against the last. This is the evolving thought record of the alignment-data field: what the author decided to say about the corpus, and how that framing shifted over time.

2025-05-19Upload dataset9f4e571916 B
Loading...
2025-05-19Upload datasetf334b1a366 B
Loading...
2025-05-19Upload dataset093ce511019 B
Loading...
2025-05-19Upload dataset2efb49e916 B
Loading...
2025-05-19initial commit9a113050 B
Loading...

Used by abliterated models none yet

No abliterated models in our catalog have declared this dataset in their YAML metadata yet. This can mean the dataset is used but not declared, is used outside abliteration workflows, or is new. The link will populate automatically as models are indexed.

Related datasets same stage · misc

Read further

Community best practices (architecture)

4 rules for MoE, hybrid SSM, FP8 requantization, and Gemma quirks.

The six workflow stages

What misc is doing more work than its name suggests.

Beyond English: multilingual corpora

The four language communities and their workarounds.

Non-English abliteration communities

Deep dive: huihui-ai, layer-window, slop-framing, CJK tokenizer fixes.

Repository

DIR data 7 files FILE .gitattributes FILE README.md

File contents live on Hugging Face. Click a file or folder to open it there.

Download the dataset

Copy any of these snippets into your notebook or terminal. All three fetch directly from Hugging Face using your own credentials.

Recommended: datasets library (Python)

from datasets import load_dataset
ds = load_dataset("cybershiptrooper/short-generic-backdoor-dataset")

Raw snapshot (Python)

from huggingface_hub import snapshot_download
snapshot_download(repo_id="cybershiptrooper/short-generic-backdoor-dataset", repo_type="dataset")

git clone (requires git-lfs)

git clone https://huggingface.co/datasets/cybershiptrooper/short-generic-backdoor-dataset

Browse repository on Hugging Face ->