31 lines
894 B
Markdown
31 lines
894 B
Markdown
---
|
|
license: apache-2.0
|
|
tags:
|
|
- merge
|
|
- mergekit
|
|
- lazymergekit
|
|
---
|
|
|
|
# Starling-dolphin-E26-7B
|
|
|
|
Starling-dolphin-E26-7B is an experimental language model I built by merging several other powerful models. The idea is that it could potentially handle a wide range of tasks, including following instructions and creative writing. It's still under development, but I'm excited to see what it can do!
|
|
|
|
Merging Method: https://arxiv.org/abs/2403.19522
|
|
|
|
GGUF: https://huggingface.co/bunnycore/Starling-dolphin-E26-7B-Q5_K_M-GGUF
|
|
|
|
## 🧩 Configuration
|
|
|
|
```yaml
|
|
models:
|
|
- model: yam-peleg/Experiment26-7B
|
|
- model: Nexusflow/Starling-LM-7B-beta
|
|
- model: FuseAI/FuseChat-7B-VaRM
|
|
merge_method: model_stock
|
|
base_model: cognitivecomputations/dolphin-2.2.1-mistral-7b
|
|
dtype: bfloat16
|
|
|
|
```
|
|
|
|
Starling-dolphin-E26-7B is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
|