Nova-14B-slerp / README.md
PSM272's picture
Upload folder using huggingface_hub
21a9daa verified
|
raw
history blame contribute delete
No virus
828 Bytes
---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- SillyTilly/google-gemma-2-9b-it
- THUDM/glm-4-9b-chat
---
# Nova-14B-slerp
Nova-14B-slerp is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
* [SillyTilly/google-gemma-2-9b-it](https://huggingface.co/SillyTilly/google-gemma-2-9b-it)
* [THUDM/glm-4-9b-chat](https://huggingface.co/THUDM/glm-4-9b-chat)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: SillyTilly/google-gemma-2-9b-it
layer_range: [0, 32]
- model: THUDM/glm-4-9b-chat
layer_range: [0, 32]
merge_method: slerp
base_model: SillyTilly/google-gemma-2-9b-it
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
```