Update README.md

README.md

@@ -1,6 +1,6 @@
 ---
 base_model:
-- NousResearch/Hermes-3-Llama-3.1-8B
+- mlabonne/Hermes-3-Llama-3.1-8B-lorablated
 library_name: transformers
 tags:
 - mergekit
@@ -8,15 +8,28 @@ tags:
 - autoquant
 - gguf
 ---
-# Hermes-3-Llama-3.1-8B-lorablated
 
-This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+# 🪽 Hermes-3-Llama-3.1-8B-lorablated
 
-This model was merged using the [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using [NousResearch/Hermes-3-Llama-3.1-8B](https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B) + Llama-3.1-8B-Instruct-abliterated-LORA as a base.
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/4Hbw5n68jKUSBQeTqQIeT.png)
+
+This is an uncensored version of [NousResearch/Hermes-3-Llama-3.1-8B](https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B) using lorablation.
+
+You can see in the following example how Hermes 3 refuses to answer a legitimate question while the abliterated model complies:
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/GM0WXDXmUU1dRJdYi-Py0.png)
 
+The recipe is simple:
+
+1. **Extraction**: We extract a LoRA adapter by comparing two models: a censored Llama 3.1 ([meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)) and an abliterated Llama 3.1 ([mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated](https://huggingface.co/mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated)).
+2. **Merge**: We merge this new LoRA adapter using [task arithmetic](https://arxiv.org/abs/2212.04089) to the censored [NousResearch/Hermes-3-Llama-3.1-8B](https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B) to abliterate it.
+
+See [this article](https://huggingface.co/blog/mlabonne/abliteration) to learn more about abliteration.
 
 ## 🧩 Configuration
 
+This model was merged using the [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using [NousResearch/Hermes-3-Llama-3.1-8B](https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B) + Llama-3.1-8B-Instruct-abliterated-LORA as a base.
+
 The following YAML configuration was used to produce this model:
 
 ```yaml
@@ -31,4 +44,4 @@ slices:
     model: NousResearch/Hermes-3-Llama-3.1-8B+Llama-3.1-8B-Instruct-abliterated-LORA
     parameters:
       weight: 1.0
-```
+```