Casual-Autopsy's picture
Update README.md
b32fd1a verified
|
raw
history blame
1.41 kB
---
library_name: transformers
tags:
- mergekit
- merge
base_model:
- bluuwhale/L3-SAO-MIX-8B-V1
- Sao10K/L3-8B-Niitama-v1
- Sao10K/L3-8B-Lunaris-v1
- Sao10K/L3-8B-Tamamo-v1
- Sao10K/L3-8B-Stheno-v3.2
---
# L3-bluuwhale-SAO-MIX-8B-V1_fp32-merge-calc
This is a remerge of [bluuwhale's merger](https://huggingface.co./bluuwhale/L3-SAO-MIX-8B-V1) using the exact yaml config with the only difference being that merge calculations are done in fp32 instead of bfp16
## Merge Details
### Merge Method
This model was merged using the della merge method using [Sao10K/L3-8B-Niitama-v1](https://huggingface.co./Sao10K/L3-8B-Niitama-v1) as a base.
### Models Merged
The following models were included in the merge:
* [Sao10K/L3-8B-Lunaris-v1](https://huggingface.co./Sao10K/L3-8B-Lunaris-v1)
* [Sao10K/L3-8B-Stheno-v3.2](https://huggingface.co./Sao10K/L3-8B-Stheno-v3.2)
* [Sao10K/L3-8B-Tamamo-v1](https://huggingface.co./Sao10K/L3-8B-Tamamo-v1)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: Sao10K/L3-8B-Lunaris-v1
parameters:
weight: 1.0
- model: Sao10K/L3-8B-Stheno-v3.2
parameters:
weight: 1.0
- model: Sao10K/L3-8B-Niitama-v1
parameters:
weight: 1.0
- model: Sao10K/L3-8B-Tamamo-v1
parameters:
weight: 1.0
base_model: Sao10K/L3-8B-Niitama-v1
merge_method: della
dtype: float32
out_dtype: bfloat16
```