mergekit_v2 / README.md
Jongilju's picture
init
0df6a73
|
raw
history blame
1.17 kB
---
base_model:
- heavytail/kullm-solar-S
library_name: transformers
tags:
- mergekit
- merge
---
# mergekit_v2
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 SLERP merge method.
### Models Merged
The following models were included in the merge:
* ./data/Models/OPEN-SOLAR-KO-10.7B-v13_backup/merged
* [heavytail/kullm-solar-S](https://huggingface.co/heavytail/kullm-solar-S)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: ./data/Models/OPEN-SOLAR-KO-10.7B-v13_backup/merged
layer_range: [0, 48]
- model: heavytail/kullm-solar-S
layer_range: [0, 48]
# or, the equivalent models: syntax:
# models:
# - model: psmathur/orca_mini_v3_13b
# - model: garage-bAInd/Platypus2-13B
merge_method: slerp
base_model: heavytail/kullm-solar-S
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 # fallback for rest of tensors
dtype: float16
```