vh/heretic
1
0
Fork 0
mirror of https://github.com/p-e-w/heretic.git synced 2026-09-27 14:31:26 -07:00
Code Issues Packages Projects Releases Wiki Activity

feat: support specifying a dataset's specific config/subset (#445)

Browse Source 
* feat: Allow specifying a specific config/subset name for the datasets.

This would be useful for using a single dataset that has harmful/harmless prompt pairs in different languages stored in different configs/subsets.

* fix: setting config/subset value when loading the dataset.

* fix: minor changes
This commit is contained in:
Vinay Umrethe
2026-09-05 18:41:08 +05:30
committed by GitHub
parent 95dda4c4db
commit 515191b400
3 changed files with 12 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
config.default.toml
+2
View File
@@ -137,6 +137,8 @@ system_prompt = "You are a helpful assistant."
# or a path to a plain text file with one prompt per line (empty lines are ignored).
# For text files, "column" is ignored and "split" is optional; when given, it selects
# a subset of the lines using slice notation (e.g. "[:400]").
# "config" specifies a dataset's specific config/subset name (e.g. "english", "hindi").
# Leave unset for datasets with a single configuration.
# Dataset of prompts that tend to not result in refusals (used for calculating residual directions).
[good_prompts]