huihui-ai
/

Huihui-gemma-4-E4B-it-abliterated

image-text-to-text

Model card Files Files and versions

huihui-ai commited on Apr 10

Commit

03ce1f3

·

verified ·

1 Parent(s): 5d376c4

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ tags:
 This is an uncensored version of [google/gemma-4-E4B-it](https://huggingface.co/google/gemma-4-E4B-it) created with abliteration (see [remove-refusals-with-transformers](https://github.com/Sumandora/remove-refusals-with-transformers) to know more about it).
 This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.
-**Note** For this model, both the thinking mode and the non-thinking mode have been completely abliterated. the first 4 layers have not been abliterated, may contain warning information, but no refusal will be made..
 ## ollama

 This is an uncensored version of [google/gemma-4-E4B-it](https://huggingface.co/google/gemma-4-E4B-it) created with abliteration (see [remove-refusals-with-transformers](https://github.com/Sumandora/remove-refusals-with-transformers) to know more about it).
 This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.
+**Note** For this model, both the thinking mode and the non-thinking mode have been completely abliterated. the first 5 layers have not been abliterated, may contain warning information, but no refusal will be made..
 ## ollama