52 lines
1.3 KiB
Markdown
52 lines
1.3 KiB
Markdown
|
---
|
||
|
|
base_model:
|
||
|
|
- KoboldAI/LLaMA2-13B-Psyfighter2
|
||
|
|
library_name: transformers
|
||
|
|
license: llama2
|
||
|
|
tags:
|
||
|
|
- mergekit
|
||
|
|
- merge
|
||
|
|
|
||
|
|
---
|
||
|
|
# Psydestroyer 20B
|
||
|
|
|
||
|
|
I self-merged KoboldAI's Psyfighter-13B to get a 20B model, hoping to make it smarter.
|
||
|
|
|
||
|
|
GGUFs: https://huggingface.co/seb-c/Psydestroyer-20B-GGUF
|
||
|
|
I have only made a Q4_K_M as that is what I tend to use when running 20Bs on my 3060 12GB, but if the demand is there I can make more.
|
||
|
|
|
||
|
|
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:
|
||
|
|
* [KoboldAI/LLaMA2-13B-Psyfighter2](https://huggingface.co/KoboldAI/LLaMA2-13B-Psyfighter2)
|
||
|
|
|
||
|
|
### Configuration
|
||
|
|
|
||
|
|
The following YAML configuration was used to produce this model:
|
||
|
|
|
||
|
|
```yaml
|
||
|
|
slices:
|
||
|
|
- sources:
|
||
|
|
- model: "KoboldAI/LLaMA2-13B-Psyfighter2"
|
||
|
|
layer_range: [0, 16]
|
||
|
|
- sources:
|
||
|
|
- model: "KoboldAI/LLaMA2-13B-Psyfighter2"
|
||
|
|
layer_range: [8, 24]
|
||
|
|
- sources:
|
||
|
|
- model: "KoboldAI/LLaMA2-13B-Psyfighter2"
|
||
|
|
layer_range: [17, 32]
|
||
|
|
- sources:
|
||
|
|
- model: "KoboldAI/LLaMA2-13B-Psyfighter2"
|
||
|
|
layer_range: [25, 40]
|
||
|
|
merge_method: passthrough
|
||
|
|
dtype: float16
|
||
|
|
|
||
|
|
```
|