Sharp11 / README.md
ClaudioItaly's picture
Upload folder using huggingface_hub
ea64f79 verified
---
base_model:
- Sao10K/Fimbulvetr-11B-v2
- Joseph717171/Cerebrum-1.0-10.7B
library_name: transformers
tags:
- mergekit
- merge
---
# merge
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:
* [Sao10K/Fimbulvetr-11B-v2](https://huggingface.co/Sao10K/Fimbulvetr-11B-v2)
* [Joseph717171/Cerebrum-1.0-10.7B](https://huggingface.co/Joseph717171/Cerebrum-1.0-10.7B)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: Joseph717171/Cerebrum-1.0-10.7B
- model: Sao10K/Fimbulvetr-11B-v2
merge_method: slerp
tokenizer_merge_method: slerp
tokenizer_parameters:
t: 0.4 # Aumentato leggermente per bilanciare meglio Fimbulvetr
base_model: Sao10K/Fimbulvetr-11B-v2
dtype: bfloat16
parameters:
t: [0, 0.3, 0.5, 0.7, 0.5, 0.3, 0] # Curva più graduale e bilanciata
temp: 1.3 # Slightly reduced per maggiore precisione
density:
- threshold: 0.2
t: 0.8
- threshold: 0.6
t: 0.5
- threshold: 0.9
t: 0.3
# Aggiunto un nuovo livello di densità per migliorare la transizione tra i modelli
additional_density:
- threshold: 0.4
t: 0.6
```