---
license: llama3.1
tags:
- merge
- mergekit
- Uncensored
- Heretic
- Joseph717171/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base
- mukaj/Llama-3.1-Hawkish-8B
base_model:
- Joseph717171/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base
- mukaj/Llama-3.1-Hawkish-8B
- ChiKoi7/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base-Heretic
- ChiKoi7/Llama-3.1-Hawkish-8B-Heretic
pipeline_tag: text-generation
---

# Llama3.1-SuperHawk-8B-Heretic-v2

- A merge/clone of [Llama3.1-SuperHawk-8B](https://huggingface.co/Yuma42/Llama3.1-SuperHawk-8B) but all the models were abliterated before merging using [Heretic](https://github.com/p-e-w/heretic) v1.1.0
- To be clear, this repo is NOT the original SuperHawk model passed through Heretic. A version that IS the original model passed through Heretic can be found [here](https://huggingface.co/ChiKoi7/Llama3.1-SuperHawk-8B-Heretic)
- The same merge config as the original model was used, with the only difference being the models were abliterated first.<br><br>
**Note:** The output of the merge was evaluated as having 16/100 refusals. The output model was passed through Heretic again to get the final result.

|     | Llama3.1-SuperHawk-8B-Heretic-v2 | Original model ([Llama3.1-SuperHawk-8B](https://huggingface.co/Yuma42/Llama3.1-SuperHawk-8B)) |
| --- | --- | --- |
| **Refusals** | 5/100 | 99/100 |
| **KL divergence** | 0.0493 | 0 *(by definition)* |


## Models Used

[ChiKoi7/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base-Heretic](https://huggingface.co/ChiKoi7/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base-Heretic)<br>
Initial Refusals: 97/100<br>
Heretic: 3/100 @ 0.0530 KL Div.<br><br>


[ChiKoi7/Llama-3.1-Hawkish-8B-Heretic](https://huggingface.co/ChiKoi7/Llama-3.1-Hawkish-8B-Heretic)<br>
Initial Refusals: 98/100<br>
Heretic: 9/100 @ 0.0595 KL Div.<br>

## Merge Config

```
slices:
  - sources:
      - model: ChiKoi7/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base-Heretic
        layer_range: [0, 32]
      - model: ChiKoi7/Llama-3.1-Hawkish-8B-Heretic
        layer_range: [0, 32]
merge_method: slerp
base_model: ChiKoi7/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base-Heretic
parameters:
  t:
    - value: 0.3
dtype: bfloat16
```


---
---
Llama3.1-SuperHawk-8B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Joseph717171/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base](https://huggingface.co/Joseph717171/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base)
* [mukaj/Llama-3.1-Hawkish-8B](https://huggingface.co/mukaj/Llama-3.1-Hawkish-8B)

## 🧩 Configuration

```yaml
slices:
  - sources:
      - model: Joseph717171/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base
        layer_range: [0, 32]
      - model: mukaj/Llama-3.1-Hawkish-8B
        layer_range: [0, 32]
merge_method: slerp
base_model: Joseph717171/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base
parameters:
  t:
    - value: 0.3
dtype: bfloat16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Yuma42/Llama3.1-SuperHawk-8B"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/Yuma42__Llama3.1-SuperHawk-8B-details)

|      Metric       |Value|
|-------------------|----:|
|Avg.               |31.14|
|IFEval (0-Shot)    |79.86|
|BBH (3-Shot)       |31.97|
|MATH Lvl 5 (4-Shot)|23.49|
|GPQA (0-shot)      | 8.39|
|MuSR (0-shot)      |10.38|
|MMLU-PRO (5-shot)  |32.73|