DreadPoor's picture
Upload folder using huggingface_hub
f647d8a verified
---
base_model:
- SentientAGI/Dobby-Mini-Unhinged-Llama-3.1-8B
- ResplendentAI/Smarts_Llama3
- DreadPoor/Yafune-8B-Model_Stock
- kloodia/lora-8b-medic
- BoltMonkey/DreadMix
- ResplendentAI/NoWarning_Llama3
- DreadPoor/Decayed-8B-LINEAR
- kloodia/lora-8b-physic
library_name: transformers
tags:
- mergekit
- merge
---
# merge
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [SentientAGI/Dobby-Mini-Unhinged-Llama-3.1-8B](https://huggingface.co/SentientAGI/Dobby-Mini-Unhinged-Llama-3.1-8B) + [ResplendentAI/Smarts_Llama3](https://huggingface.co/ResplendentAI/Smarts_Llama3) as a base.
### Models Merged
The following models were included in the merge:
* [DreadPoor/Yafune-8B-Model_Stock](https://huggingface.co/DreadPoor/Yafune-8B-Model_Stock) + [kloodia/lora-8b-medic](https://huggingface.co/kloodia/lora-8b-medic)
* [BoltMonkey/DreadMix](https://huggingface.co/BoltMonkey/DreadMix) + [ResplendentAI/NoWarning_Llama3](https://huggingface.co/ResplendentAI/NoWarning_Llama3)
* [DreadPoor/Decayed-8B-LINEAR](https://huggingface.co/DreadPoor/Decayed-8B-LINEAR) + [kloodia/lora-8b-physic](https://huggingface.co/kloodia/lora-8b-physic)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: DreadPoor/Yafune-8B-Model_Stock+kloodia/lora-8b-medic
- model: DreadPoor/Decayed-8B-LINEAR+kloodia/lora-8b-physic
- model: BoltMonkey/DreadMix+ResplendentAI/NoWarning_Llama3
merge_method: model_stock
base_model: SentientAGI/Dobby-Mini-Unhinged-Llama-3.1-8B+ResplendentAI/Smarts_Llama3
normalize: true
int8_mask: true
dtype: bfloat16
```