Domain-Fusion-L3-8B / README.md
Nitral-AI's picture
Update README.md
96ab6f7 verified
|
raw
history blame contribute delete
No virus
979 Bytes
---
base_model: []
library_name: transformers
tags:
- mergekit
- merge
license: other
language:
- en
---
![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/0NR7YD-XuOZBCQIP1jcjJ.jpeg)
# Domain-Fusion-L3-8B
# Recomended ST Presets: [Domain Fusion Presets](https://huggingface.co/Nitral-AI/Domain-Fusion-L3-8B/tree/main/Domain_Fusion-Presets)
---
### Models Merged
Lineage of internal models: Hathor 0.1 x Poppy_0.72 = Hathor_Variant-X (slerp) | T-900 x Biollm = T-900xBioLLM. (slerp)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: ./Hathor_Variant-X
layer_range: [0, 32]
- model: ./T-900xBioLLM
layer_range: [0, 32]
merge_method: slerp
base_model: ./Hathor_Variant-X
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
```