MiquMaid-120B / README.md
Undi95's picture
Upload folder using huggingface_hub
a94dd16 verified
|
raw
history blame
1.4 kB
---
base_model:
- Undi95/Miqu-MS-70B
- NeverSleep/MiquMaid-v3-70B
library_name: transformers
tags:
- mergekit
- merge
---
# MiquMaid-120B
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the passthrough merge method.
### Models Merged
The following models were included in the merge:
* [Undi95/Miqu-MS-70B](https://huggingface.co/Undi95/Miqu-MS-70B)
* [NeverSleep/MiquMaid-v3-70B](https://huggingface.co/NeverSleep/MiquMaid-v3-70B)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: NeverSleep/MiquMaid-v3-70B
layer_range: [0, 16]
- sources:
- model: Undi95/Miqu-MS-70B
layer_range: [8, 24]
- sources:
- model: NeverSleep/MiquMaid-v3-70B
layer_range: [17, 32]
- sources:
- model: Undi95/Miqu-MS-70B
layer_range: [25, 40]
- sources:
- model: NeverSleep/MiquMaid-v3-70B
layer_range: [33, 48]
- sources:
- model: Undi95/Miqu-MS-70B
layer_range: [41, 56]
- sources:
- model: NeverSleep/MiquMaid-v3-70B
layer_range: [49, 64]
- sources:
- model: Undi95/Miqu-MS-70B
layer_range: [57, 72]
- sources:
- model: NeverSleep/MiquMaid-v3-70B
layer_range: [65, 80]
merge_method: passthrough
dtype: bfloat16
```