denru's picture
Upload folder using huggingface_hub
ef33537 verified
|
raw
history blame
1.53 kB
---
base_model:
- sophosympatheia/Midnight-Miqu-70B-v1.5
library_name: transformers
tags:
- mergekit
- merge
---
# merged_model
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:
* [sophosympatheia/Midnight-Miqu-70B-v1.5](https://huggingface.co./sophosympatheia/Midnight-Miqu-70B-v1.5)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: sophosympatheia/Midnight-Miqu-70B-v1.5
layer_range: [0, 16]
- sources:
- model: sophosympatheia/Midnight-Miqu-70B-v1.5
layer_range: [8, 24]
- sources:
- model: sophosympatheia/Midnight-Miqu-70B-v1.5
layer_range: [16, 32]
- sources:
- model: sophosympatheia/Midnight-Miqu-70B-v1.5
layer_range: [24, 40]
- sources:
- model: sophosympatheia/Midnight-Miqu-70B-v1.5
layer_range: [32, 48]
- sources:
- model: sophosympatheia/Midnight-Miqu-70B-v1.5
layer_range: [40, 56]
- sources:
- model: sophosympatheia/Midnight-Miqu-70B-v1.5
layer_range: [48, 64]
- sources:
- model: sophosympatheia/Midnight-Miqu-70B-v1.5
layer_range: [56, 72]
- sources:
- model: sophosympatheia/Midnight-Miqu-70B-v1.5
layer_range: [64, 80]
merge_method: passthrough
dtype: float16
```