---
base_model:
- ammarali32/multi_verse_model
- jeiku/Theory_of_Mind_Roleplay_Mistral
- ammarali32/multi_verse_model
- jeiku/Alpaca_NSFW_Shuffled_Mistral
- ammarali32/multi_verse_model
- jeiku/Theory_of_Mind_Mistral
- ammarali32/multi_verse_model
- jeiku/Gnosis_Reformatted_Mistral
- ammarali32/multi_verse_model
- ammarali32/multi_verse_model
- jeiku/Re-Host_Limarp_Mistral
- ammarali32/multi_verse_model
- jeiku/Luna_LoRA_Mistral
library_name: transformers
license: cc-by-nc-4.0
tags:
- mergekit
- merge
language:
- en
---

![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/63df7c44f0c75dfb876272c0/EjMKmAvmKoKd_Z7o0b3VK.jpeg)
Multi verse img!
# merge

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

## Merge Details
* This merge is entirely experimental, I've only tested it a few times but it seems to work? Thanks for all the loras jeiku. I keep getting driver crashes training my own :\
* Update, It scores well! My highest scoring model so far
* Self testing results, it can handle non-human characters surprisingly well and does well seperating human actions from non-human actions. I'm happy with it :3
* Works with alpaca best, Loras' are alpaca. But works with chatml too! 
### Merge Method

This model was merged using the [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using [ammarali32/multi_verse_model](https://huggingface.co/ammarali32/multi_verse_model) as a base.

### Models Merged

The following models were included in the merge:
* [ammarali32/multi_verse_model](https://huggingface.co/ammarali32/multi_verse_model) + [jeiku/Theory_of_Mind_Roleplay_Mistral](https://huggingface.co/jeiku/Theory_of_Mind_Roleplay_Mistral)
* [ammarali32/multi_verse_model](https://huggingface.co/ammarali32/multi_verse_model) + [jeiku/Alpaca_NSFW_Shuffled_Mistral](https://huggingface.co/jeiku/Alpaca_NSFW_Shuffled_Mistral)
* [ammarali32/multi_verse_model](https://huggingface.co/ammarali32/multi_verse_model) + [jeiku/Theory_of_Mind_Mistral](https://huggingface.co/jeiku/Theory_of_Mind_Mistral)
* [ammarali32/multi_verse_model](https://huggingface.co/ammarali32/multi_verse_model) + [jeiku/Gnosis_Reformatted_Mistral](https://huggingface.co/jeiku/Gnosis_Reformatted_Mistral)
* [ammarali32/multi_verse_model](https://huggingface.co/ammarali32/multi_verse_model) + [jeiku/Re-Host_Limarp_Mistral](https://huggingface.co/jeiku/Re-Host_Limarp_Mistral)
* [ammarali32/multi_verse_model](https://huggingface.co/ammarali32/multi_verse_model) + [jeiku/Luna_LoRA_Mistral](https://huggingface.co/jeiku/Luna_LoRA_Mistral)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
merge_method: task_arithmetic
base_model: ammarali32/multi_verse_model
parameters:
  normalize: true
models:
  - model: ammarali32/multi_verse_model+jeiku/Gnosis_Reformatted_Mistral
    parameters:
      weight: 0.7
  - model: ammarali32/multi_verse_model+jeiku/Theory_of_Mind_Roleplay_Mistral
    parameters:
      weight: 0.65
  - model: ammarali32/multi_verse_model+jeiku/Luna_LoRA_Mistral
    parameters:
      weight: 0.5
  - model: ammarali32/multi_verse_model+jeiku/Re-Host_Limarp_Mistral
    parameters:
      weight: 0.8
  - model: ammarali32/multi_verse_model+jeiku/Alpaca_NSFW_Shuffled_Mistral
    parameters:
      weight: 0.75  
  - model: ammarali32/multi_verse_model+jeiku/Theory_of_Mind_Mistral
    parameters:
      weight: 0.7                     
dtype: float16

```
# [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__Multi-Verse-RP-7B)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |74.73|
|AI2 Reasoning Challenge (25-Shot)|72.35|
|HellaSwag (10-Shot)              |88.37|
|MMLU (5-Shot)                    |63.94|
|TruthfulQA (0-shot)              |73.19|
|Winogrande (5-shot)              |84.14|
|GSM8k (5-shot)                   |66.41|