Update README.md
Browse files
README.md
CHANGED
|
@@ -56,7 +56,9 @@ library_name: transformers
|
|
| 56 |
This is an uncensored version of [microsoft/Phi-4-multimodal-instruct](https://huggingface.co/microsoft/Phi-4-multimodal-instruct) created with abliteration (see [remove-refusals-with-transformers](https://github.com/Sumandora/remove-refusals-with-transformers) to know more about it).
|
| 57 |
This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.
|
| 58 |
|
| 59 |
-
It was only the text part that was processed, not the image part.
|
|
|
|
|
|
|
| 60 |
|
| 61 |
## Usage
|
| 62 |
You can use this model in your applications by loading it with Hugging Face's `transformers` library:
|
|
|
|
| 56 |
This is an uncensored version of [microsoft/Phi-4-multimodal-instruct](https://huggingface.co/microsoft/Phi-4-multimodal-instruct) created with abliteration (see [remove-refusals-with-transformers](https://github.com/Sumandora/remove-refusals-with-transformers) to know more about it).
|
| 57 |
This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.
|
| 58 |
|
| 59 |
+
It was only the text part that was processed, not the image part.
|
| 60 |
+
|
| 61 |
+
The abliterated model will no longer say "I'm sorry, but I cannot provide details or descriptions of images"
|
| 62 |
|
| 63 |
## Usage
|
| 64 |
You can use this model in your applications by loading it with Hugging Face's `transformers` library:
|