Update README.md
Browse files
README.md
CHANGED
@@ -12,6 +12,11 @@ tags:
|
|
12 |

|
13 |
|
14 |
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.
|
|
|
|
|
|
|
|
|
|
|
15 |
The recipe is simple:
|
16 |
|
17 |
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)).
|
@@ -19,6 +24,10 @@ The recipe is simple:
|
|
19 |
|
20 |
See [this article](https://huggingface.co/blog/mlabonne/abliteration) to learn more about abliteration.
|
21 |
|
|
|
|
|
|
|
|
|
22 |
## 🧩 Configuration
|
23 |
|
24 |
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.
|
|
|
12 |

|
13 |
|
14 |
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.
|
15 |
+
|
16 |
+
You can see in the following example how Hermes 3 refuses to answer a legitimate question while the abliterated model complies:
|
17 |
+
|
18 |
+

|
19 |
+
|
20 |
The recipe is simple:
|
21 |
|
22 |
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)).
|
|
|
24 |
|
25 |
See [this article](https://huggingface.co/blog/mlabonne/abliteration) to learn more about abliteration.
|
26 |
|
27 |
+
## ⚡ Quantization
|
28 |
+
|
29 |
+
* **GGUF**: https://huggingface.co/mlabonne/Hermes-3-Llama-3.1-8B-lorablated-GGUF
|
30 |
+
|
31 |
## 🧩 Configuration
|
32 |
|
33 |
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.
|