61 lines
1.2 KiB
Markdown
61 lines
1.2 KiB
Markdown
---
|
|
base_model:
|
|
- nbeerbower/HumanLlama-3.2-1B
|
|
- juiceb0xc0de/bella-bartender-heretic-1b
|
|
library_name: transformers
|
|
tags:
|
|
- mergekit
|
|
- merge
|
|
|
|
---
|
|
# Podredumbre 3.2 1B
|
|
|
|
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](https://en.wikipedia.org/wiki/Slerp) merge method.
|
|
|
|
### Models Merged
|
|
|
|
The following models were included in the merge:
|
|
* [nbeerbower/HumanLlama-3.2-1B](https://huggingface.co/nbeerbower/HumanLlama-3.2-1B)
|
|
* [juiceb0xc0de/bella-bartender-heretic-1b](https://huggingface.co/juiceb0xc0de/bella-bartender-heretic-1b)
|
|
|
|
### Configuration
|
|
|
|
The following YAML configuration was used to produce this model:
|
|
|
|
```yaml
|
|
|
|
|
|
# =========================
|
|
# Podredumbre-3.2-1B
|
|
# Human-class B.O.W. (Infected Host)
|
|
# =========================
|
|
|
|
merge_method: slerp
|
|
dtype: float32
|
|
out_dtype: float32
|
|
|
|
base_model: nbeerbower/HumanLlama-3.2-1B
|
|
|
|
models:
|
|
- model: nbeerbower/HumanLlama-3.2-1B
|
|
parameters:
|
|
weight: 0.55
|
|
- model: juiceb0xc0de/bella-bartender-heretic-1b
|
|
parameters:
|
|
weight: 0.45
|
|
|
|
parameters:
|
|
t: 0.45
|
|
normalize: false
|
|
rescale: true
|
|
rescale_factor: 1.12
|
|
memory_efficient: true
|
|
|
|
|
|
```
|