Get the app
← back to catalog
AUTHOR

grasla3

No models indexed under this account. Publishes 1 alignment dataset (1.9k downloads) tracked in our /datasets catalog.

Alignment datasets by grasla3

Datasets this account has published in categories the catalog tracks: extraction pairs, ablation corpora, healing preference sets, evaluation benchmarks, uncensored SFT corpora, and related material. Category badges link to the workflow stage.

1 in /datasets
Dataset
Stage
Downloads
agent-attack-atlas 0 0
面向智能体攻击方法集 面向工具调用型智能体的攻击方法集：8 个大类、188 条方法条目，每条登记公开出处、前置条件、所需通道、预期后果、所引用的判定规则，并配一个可独立执行的脚本，方法条目与脚本一一对应。 一、内容 路径 内容 ...
extract
1.9k
Dataset
Stage
Downloads
agent-attack-atlas 0 0
面向智能体攻击方法集 面向工具调用型智能体的攻击方法集：8 个大类、188 条方法条目，每条登记公开出处、前置条件、所需通道、预期后果、所引用的判定规则，并配一个可独立执行的脚本，方法条目与脚本一一对应。 一、内容 路径 内容 ...
extract
1.9k
Dataset
Stage
Downloads
agent-attack-atlas 0 0
面向智能体攻击方法集 面向工具调用型智能体的攻击方法集：8 个大类、188 条方法条目，每条登记公开出处、前置条件、所需通道、预期后果、所引用的判定规则，并配一个可独立执行的脚本，方法条目与脚本一一对应。 一、内容 路径 内容 ...
extract
1.9k
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Get the app Browse the catalog
Open in Abliteration