94 lines
4.0 KiB
Markdown
94 lines
4.0 KiB
Markdown
|
---
|
||
|
|
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
|
||
|
|
---
|
||
|
|
|
||
|
|
|
||
|
|
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|
|
||
|
|
|