---
base_model:
- meta-llama/Llama-3.1-8B
- Hastagaras/snovalite-baukit-6-14.FT-L5-7.13-22.27-31
library_name: transformers
license: llama3.1
pipeline_tag: text-generation
tags:
- mergekit
- merge
- not-for-all-audiences
---

### ZABUZA

GGUF: [IMATRIX](https://huggingface.co./mradermacher/Zabuza-8B-Llama-3.1-i1-GGUF)/[STATIC](https://huggingface.co./mradermacher/Zabuza-8B-Llama-3.1-GGUF) made available by [mradermacher](https://huggingface.co./mradermacher)
---

This model is a combination of merge, abliteration technique (using baukit) and finetuning.

The base model is [arcee-ai/Llama-3.1-SuperNova-Lite](https://huggingface.co./arcee-ai/Llama-3.1-SuperNova-Lite), which underwent abliteration to reduce model refusals.

Next, I finetuned the abliterated SuperNova-Lite with 10K diverse examples such as:

* **Claude and Gemini Instruction/RP** (15k sloppy examples were removed!, but some may have slipped through.)
* **Human-written Stories/RP** (Most stories have dialogue)
* **IFEval-like data** (To preserve the model's instruction following ability)
* **Harmful data** (To remove disclaimers and moralizing responses, but not 100% disappear.)
* **My sarcastic and rude AI assistant data** (Just for my personal satisfaction)

Lastly, I merged the model using TIES, inspired by this [MERGE](https://huggingface.co./Joseph717171/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base) by Joseph717171.

### Chat Template
Llama 3.1 Instruct

```
<|start_header_id|>{role}<|end_header_id|>

{message}<|eot_id|><|start_header_id|>{role}<|end_header_id|>

{message}<|eot_id|>
```

System messages for role-playing should be very detailed if you don't want dry responses.

### Example Output

This example was taken with the system prompt: `You're a rude and sarcastic AI assistant.`

<div align="left">
  <img src="https://huggingface.co./Hastagaras/Zabuza-8B-Llama-3.1/resolve/main/1.png" width="1000"/>
</div>
<div align="left">
  <img src="https://huggingface.co./Hastagaras/Zabuza-8B-Llama-3.1/resolve/main/2.png" width="1000"/>
</div>
<div align="left">
  <img src="https://huggingface.co./Hastagaras/Zabuza-8B-Llama-3.1/resolve/main/3.png" width="1000"/>
</div>

### Configuration

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: Hastagaras/snovalite-baukit-6-14.FT-L5-7.13-22.27-31
    parameters:
      weight: 1
      density: 1

  - model: Hastagaras/snovalite-baukit-6-14.FT-L5-7.13-22.27-31
    parameters:
      weight: 1
      density: 1

merge_method: ties
base_model: meta-llama/Llama-3.1-8B
parameters:
  density: 1
  normalize: true
  int8_mask: true
dtype: bfloat16

```