36 lines
983 B
Markdown
36 lines
983 B
Markdown
---
|
|
license: apache-2.0
|
|
tags:
|
|
- merge
|
|
- mergekit
|
|
- arcee-ai/sec-mistral-7b-instruct-1.2-epoch
|
|
- MaziyarPanahi/Calme-7B-Instruct-v0.2
|
|
---
|
|
|
|
# SEC-Calme-7B-Instruct
|
|
|
|
SEC-Calme-7B-Instruct is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
|
|
* [arcee-ai/sec-mistral-7b-instruct-1.2-epoch](https://huggingface.co/arcee-ai/sec-mistral-7b-instruct-1.2-epoch)
|
|
* [MaziyarPanahi/Calme-7B-Instruct-v0.2](https://huggingface.co/MaziyarPanahi/Calme-7B-Instruct-v0.2)
|
|
|
|
## 🧩 Configuration
|
|
|
|
```yaml
|
|
slices:
|
|
- sources:
|
|
- model: arcee-ai/sec-mistral-7b-instruct-1.2-epoch
|
|
layer_range: [0, 32]
|
|
- model: MaziyarPanahi/Calme-7B-Instruct-v0.2
|
|
layer_range: [0, 32]
|
|
merge_method: slerp
|
|
base_model: arcee-ai/sec-mistral-7b-instruct-1.2-epoch
|
|
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
|
|
|
|
``` |