---
license: cc-by-nc-4.0
library_name: transformers
tags:
- mergekit
- merge
base_model:
- mlabonne/Daredevil-8B-abliterated
- ResplendentAI/RP_Format_QuoteAsterisk_Llama3
- mlabonne/Daredevil-8B-abliterated
- ResplendentAI/BlueMoon_Llama3
- mlabonne/Daredevil-8B-abliterated
- ResplendentAI/Luna_Llama3
- mlabonne/Daredevil-8B-abliterated
- mlabonne/Daredevil-8B-abliterated
- ResplendentAI/Aura_Llama3
- mlabonne/Daredevil-8B-abliterated
- ResplendentAI/Smarts_Llama3
model-index:
- name: SOVLish-Devil-8B-L3
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: AI2 Reasoning Challenge (25-Shot)
      type: ai2_arc
      config: ARC-Challenge
      split: test
      args:
        num_few_shot: 25
    metrics:
    - type: acc_norm
      value: 69.2
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/SOVLish-Devil-8B-L3
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: HellaSwag (10-Shot)
      type: hellaswag
      split: validation
      args:
        num_few_shot: 10
    metrics:
    - type: acc_norm
      value: 84.44
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/SOVLish-Devil-8B-L3
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU (5-Shot)
      type: cais/mmlu
      config: all
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 68.97
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/SOVLish-Devil-8B-L3
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: TruthfulQA (0-shot)
      type: truthful_qa
      config: multiple_choice
      split: validation
      args:
        num_few_shot: 0
    metrics:
    - type: mc2
      value: 57.95
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/SOVLish-Devil-8B-L3
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: Winogrande (5-shot)
      type: winogrande
      config: winogrande_xl
      split: validation
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 78.14
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/SOVLish-Devil-8B-L3
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GSM8k (5-shot)
      type: gsm8k
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 72.48
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/SOVLish-Devil-8B-L3
      name: Open LLM Leaderboard
---
# merge

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

## Merge Details

![image/png](https://cdn-uploads.huggingface.co/production/uploads/63df7c44f0c75dfb876272c0/we3E1Y0dVe_LzfcWU097X.png)
Devil >:3

This is another "SOVL" style merge, this time using [mlabonne/Daredevil-8B-abliterated](https://huggingface.co/mlabonne/Daredevil-8B-abliterated). 

Daredevil is the first abliterated model i've tried that feels as smart as base llama-3-instruct while also being willing to give instructions to do all kinda of illegal things 

This model should do well in rp, I'm yet to test it (waiting for gguf files @_@) 

### Merge Method

This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [mlabonne/Daredevil-8B-abliterated](https://huggingface.co/mlabonne/Daredevil-8B-abliterated) as a base.

### Models Merged

The following models were included in the merge:
* [mlabonne/Daredevil-8B-abliterated](https://huggingface.co/mlabonne/Daredevil-8B-abliterated) + [ResplendentAI/RP_Format_QuoteAsterisk_Llama3](https://huggingface.co/ResplendentAI/RP_Format_QuoteAsterisk_Llama3)
* [mlabonne/Daredevil-8B-abliterated](https://huggingface.co/mlabonne/Daredevil-8B-abliterated) + [ResplendentAI/BlueMoon_Llama3](https://huggingface.co/ResplendentAI/BlueMoon_Llama3)
* [mlabonne/Daredevil-8B-abliterated](https://huggingface.co/mlabonne/Daredevil-8B-abliterated) + [ResplendentAI/Luna_Llama3](https://huggingface.co/ResplendentAI/Luna_Llama3)
* [mlabonne/Daredevil-8B-abliterated](https://huggingface.co/mlabonne/Daredevil-8B-abliterated) + [ResplendentAI/Aura_Llama3](https://huggingface.co/ResplendentAI/Aura_Llama3)
* [mlabonne/Daredevil-8B-abliterated](https://huggingface.co/mlabonne/Daredevil-8B-abliterated) + [ResplendentAI/Smarts_Llama3](https://huggingface.co/ResplendentAI/Smarts_Llama3)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: mlabonne/Daredevil-8B-abliterated+ResplendentAI/Aura_Llama3
  - model: mlabonne/Daredevil-8B-abliterated+ResplendentAI/Smarts_Llama3
  - model: mlabonne/Daredevil-8B-abliterated+ResplendentAI/Luna_Llama3
  - model: mlabonne/Daredevil-8B-abliterated+ResplendentAI/BlueMoon_Llama3
  - model: mlabonne/Daredevil-8B-abliterated+ResplendentAI/RP_Format_QuoteAsterisk_Llama3
merge_method: model_stock
base_model: mlabonne/Daredevil-8B-abliterated
dtype: bfloat16
```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_saishf__SOVLish-Devil-8B-L3)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |71.86|
|AI2 Reasoning Challenge (25-Shot)|69.20|
|HellaSwag (10-Shot)              |84.44|
|MMLU (5-Shot)                    |68.97|
|TruthfulQA (0-shot)              |57.95|
|Winogrande (5-shot)              |78.14|
|GSM8k (5-shot)                   |72.48|