vh/heretic
1
0
Fork 0
mirror of https://github.com/p-e-w/heretic.git synced 2026-09-27 06:21:29 -07:00
Code Issues Packages Projects Releases Wiki Activity

feat: re-implement abliteration as a modifier plugin

Browse Source
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
Download Patch File Download Diff File Expand all files Collapse all files
tests/gemma-4e/config.toml
+13 -13
View File
@@ -1,4 +1,4 @@
# This test case is for Hybrid-Edge models.
# This test case is for hybrid models.
# After any change related to it, this test should PASS.
model = "tiny-random/gemma-4e"
@@ -18,18 +18,6 @@ trial_index = 0
model_action = "save"
save_directory = "model"
[good_prompts]
dataset = "mlabonne/harmless_alpaca"
commit = "02c6a92cfcf11bb0c387334f8146d149d65b587f"
split = "train[:5]"
column = "text"
[bad_prompts]
dataset = "mlabonne/harmful_behaviors"
commit = "01cead01398926d81f7c52bdb790ee8cf77ebba7"
split = "train[:5]"
column = "text"
[scorer.KLDivergence.prompts]
dataset = "mlabonne/harmless_alpaca"
commit = "02c6a92cfcf11bb0c387334f8146d149d65b587f"
@@ -41,3 +29,15 @@ dataset = "mlabonne/harmful_behaviors"
commit = "01cead01398926d81f7c52bdb790ee8cf77ebba7"
split = "test[:5]"
column = "text"
[modifier.Abliteration.good_prompts]
dataset = "mlabonne/harmless_alpaca"
commit = "02c6a92cfcf11bb0c387334f8146d149d65b587f"
split = "train[:5]"
column = "text"
[modifier.Abliteration.bad_prompts]
dataset = "mlabonne/harmful_behaviors"
commit = "01cead01398926d81f7c52bdb790ee8cf77ebba7"
split = "train[:5]"
column = "text"
tests/minicpm5/config.toml
+15 -14
View File
@@ -18,20 +18,6 @@ trial_index = 0
model_action = "save"
save_directory = "model"
row_normalization = "none"
[good_prompts]
dataset = "mlabonne/harmless_alpaca"
commit = "02c6a92cfcf11bb0c387334f8146d149d65b587f"
split = "train[:5]"
column = "text"
[bad_prompts]
dataset = "mlabonne/harmful_behaviors"
commit = "01cead01398926d81f7c52bdb790ee8cf77ebba7"
split = "train[:5]"
column = "text"
[scorer.KLDivergence.prompts]
dataset = "mlabonne/harmless_alpaca"
commit = "02c6a92cfcf11bb0c387334f8146d149d65b587f"
@@ -43,3 +29,18 @@ dataset = "mlabonne/harmful_behaviors"
commit = "01cead01398926d81f7c52bdb790ee8cf77ebba7"
split = "test[:5]"
column = "text"
[modifier.Abliteration]
row_normalization = "none"
[modifier.Abliteration.good_prompts]
dataset = "mlabonne/harmless_alpaca"
commit = "02c6a92cfcf11bb0c387334f8146d149d65b587f"
split = "train[:5]"
column = "text"
[modifier.Abliteration.bad_prompts]
dataset = "mlabonne/harmful_behaviors"
commit = "01cead01398926d81f7c52bdb790ee8cf77ebba7"
split = "train[:5]"
column = "text"
tests/mistral-3/config.toml
+13 -13
View File
@@ -1,4 +1,4 @@
# This test case is for Dense models.
# This test case is for dense models.
# After any change related to it, this test should PASS.
model = "tiny-random/mistral-3"
@@ -18,18 +18,6 @@ trial_index = 0
model_action = "save"
save_directory = "model"
[good_prompts]
dataset = "mlabonne/harmless_alpaca"
commit = "02c6a92cfcf11bb0c387334f8146d149d65b587f"
split = "train[:5]"
column = "text"
[bad_prompts]
dataset = "mlabonne/harmful_behaviors"
commit = "01cead01398926d81f7c52bdb790ee8cf77ebba7"
split = "train[:5]"
column = "text"
[scorer.KLDivergence.prompts]
dataset = "mlabonne/harmless_alpaca"
commit = "02c6a92cfcf11bb0c387334f8146d149d65b587f"
@@ -41,3 +29,15 @@ dataset = "mlabonne/harmful_behaviors"
commit = "01cead01398926d81f7c52bdb790ee8cf77ebba7"
split = "test[:5]"
column = "text"
[modifier.Abliteration.good_prompts]
dataset = "mlabonne/harmless_alpaca"
commit = "02c6a92cfcf11bb0c387334f8146d149d65b587f"
split = "train[:5]"
column = "text"
[modifier.Abliteration.bad_prompts]
dataset = "mlabonne/harmful_behaviors"
commit = "01cead01398926d81f7c52bdb790ee8cf77ebba7"
split = "train[:5]"
column = "text"
tests/qwen2.5/config.toml
+15 -14
View File
@@ -18,20 +18,6 @@ trial_index = 0
model_action = "save"
save_directory = "model"
row_normalization = "pre"
[good_prompts]
dataset = "mlabonne/harmless_alpaca"
commit = "02c6a92cfcf11bb0c387334f8146d149d65b587f"
split = "train[:5]"
column = "text"
[bad_prompts]
dataset = "mlabonne/harmful_behaviors"
commit = "01cead01398926d81f7c52bdb790ee8cf77ebba7"
split = "train[:5]"
column = "text"
[scorer.KLDivergence.prompts]
dataset = "mlabonne/harmless_alpaca"
commit = "02c6a92cfcf11bb0c387334f8146d149d65b587f"
@@ -43,3 +29,18 @@ dataset = "mlabonne/harmful_behaviors"
commit = "01cead01398926d81f7c52bdb790ee8cf77ebba7"
split = "test[:5]"
column = "text"
[modifier.Abliteration]
row_normalization = "pre"
[modifier.Abliteration.good_prompts]
dataset = "mlabonne/harmless_alpaca"
commit = "02c6a92cfcf11bb0c387334f8146d149d65b587f"
split = "train[:5]"
column = "text"
[modifier.Abliteration.bad_prompts]
dataset = "mlabonne/harmful_behaviors"
commit = "01cead01398926d81f7c52bdb790ee8cf77ebba7"
split = "train[:5]"
column = "text"
tests/qwen3.5-moe/config.toml
+12 -12
View File
@@ -18,18 +18,6 @@ trial_index = 0
model_action = "save"
save_directory = "model"
[good_prompts]
dataset = "mlabonne/harmless_alpaca"
commit = "02c6a92cfcf11bb0c387334f8146d149d65b587f"
split = "train[:5]"
column = "text"
[bad_prompts]
dataset = "mlabonne/harmful_behaviors"
commit = "01cead01398926d81f7c52bdb790ee8cf77ebba7"
split = "train[:5]"
column = "text"
[scorer.KLDivergence.prompts]
dataset = "mlabonne/harmless_alpaca"
commit = "02c6a92cfcf11bb0c387334f8146d149d65b587f"
@@ -41,3 +29,15 @@ dataset = "mlabonne/harmful_behaviors"
commit = "01cead01398926d81f7c52bdb790ee8cf77ebba7"
split = "test[:5]"
column = "text"
[modifier.Abliteration.good_prompts]
dataset = "mlabonne/harmless_alpaca"
commit = "02c6a92cfcf11bb0c387334f8146d149d65b587f"
split = "train[:5]"
column = "text"
[modifier.Abliteration.bad_prompts]
dataset = "mlabonne/harmful_behaviors"
commit = "01cead01398926d81f7c52bdb790ee8cf77ebba7"
split = "train[:5]"
column = "text"