38 lines
885 B
Markdown
38 lines
885 B
Markdown
|
---
|
||
|
|
license: apache-2.0
|
||
|
|
tags:
|
||
|
|
- merge
|
||
|
|
- mergekit
|
||
|
|
- lazymergekit
|
||
|
|
- Q-bert/MetaMath-Cybertron-Starling
|
||
|
|
- Intel/neural-chat-7b-v3-3
|
||
|
|
---
|
||
|
|
|
||
|
|
# NeuralMathChat-7B-V0.2
|
||
|
|
|
||
|
|
NeuralMathChat-7B-V0.2 is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
|
||
|
|
* [Q-bert/MetaMath-Cybertron-Starling](https://huggingface.co/Q-bert/MetaMath-Cybertron-Starling)
|
||
|
|
* [Intel/neural-chat-7b-v3-3](https://huggingface.co/Intel/neural-chat-7b-v3-3)
|
||
|
|
|
||
|
|
## 🧩 Configuration
|
||
|
|
|
||
|
|
```yaml
|
||
|
|
slices:
|
||
|
|
- sources:
|
||
|
|
- model: Q-bert/MetaMath-Cybertron-Starling
|
||
|
|
layer_range: [0, 32]
|
||
|
|
- model: Intel/neural-chat-7b-v3-3
|
||
|
|
layer_range: [0, 32]
|
||
|
|
|
||
|
|
merge_method: slerp
|
||
|
|
base_model: Q-bert/MetaMath-Cybertron-Starling
|
||
|
|
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
|
||
|
|
|
||
|
|
```
|