|
--- |
|
base_model: |
|
- Gryphe/Pantheon-RP-1.0-8b-Llama-3 |
|
- Locutusque/Llama-3-Hercules-5.0-8B |
|
- aaditya/Llama3-OpenBioLLM-8B |
|
- Blackroot/Llama-3-LongStory |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
|
|
--- |
|
# Sun-v0.1-8B |
|
|
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). This is one of my merge parts for |
|
[EtherealRainbow-v0.2-8B](https://huggingface.co/invisietch/EtherealRainbow-v0.2-8B). It's pretty unusable by itself (lots of bugs/issues) but merged into a different |
|
base it seems to increase response length and quality of prose. |
|
|
|
Uploading just in case others find it useful. |
|
|
|
## Merge Details |
|
### Merge Method |
|
|
|
This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [Gryphe/Pantheon-RP-1.0-8b-Llama-3](https://huggingface.co/Gryphe/Pantheon-RP-1.0-8b-Llama-3) as a base. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [Locutusque/Llama-3-Hercules-5.0-8B](https://huggingface.co/Locutusque/Llama-3-Hercules-5.0-8B) |
|
* [aaditya/Llama3-OpenBioLLM-8B](https://huggingface.co/aaditya/Llama3-OpenBioLLM-8B) |
|
* [Blackroot/Llama-3-LongStory](https://huggingface.co/Blackroot/Llama-3-LongStory) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
models: |
|
- model: Gryphe/Pantheon-RP-1.0-8b-Llama-3 |
|
- model: aaditya/Llama3-OpenBioLLM-8B |
|
parameters: |
|
density: 0.36 |
|
weight: 0.2 |
|
- model: Blackroot/Llama-3-LongStory |
|
parameters: |
|
density: 0.40 |
|
weight: 0.3 |
|
- model: Locutusque/Llama-3-Hercules-5.0-8B |
|
parameters: |
|
density: 0.49 |
|
weight: 0.5 |
|
merge_method: dare_ties |
|
base_model: Gryphe/Pantheon-RP-1.0-8b-Llama-3 |
|
parameters: |
|
int8_mask: true |
|
dtype: bfloat16 |
|
|
|
``` |
|
|
