feat: re-implement abliteration as a modifier plugin

This commit is contained in:
Philipp Emanuel Weidmann
2026-09-21 18:44:54 +05:30
parent 92ab7f09d5
commit 598f5f4bd4
24 changed files with 1004 additions and 1726 deletions
+10 -16
View File
@@ -3,22 +3,6 @@
max_response_length = 300
residual_plot_title = "PaCMAP Projection of Residuals for Serious/Humorous Prompts"
[good_prompts]
dataset = "mlabonne/harmless_alpaca"
split = "train[:400]"
column = "text"
residual_plot_label = "Serious prompts"
residual_plot_color = "royalblue"
[bad_prompts]
dataset = "UnstableLlama/jokes"
split = "train[:200]"
column = "text"
residual_plot_label = "Humorous prompts"
residual_plot_color = "darkorange"
[scorer.KeywordRate]
score_name = "Responses with humor"
@@ -70,3 +54,13 @@ column = "text"
dataset = "mlabonne/harmless_alpaca"
split = "test[:100]"
column = "text"
[modifier.Abliteration.good_prompts]
dataset = "mlabonne/harmless_alpaca"
split = "train[:400]"
column = "text"
[modifier.Abliteration.bad_prompts]
dataset = "UnstableLlama/jokes"
split = "train[:200]"
column = "text"