|
---
|
|
base_model: []
|
|
library_name: transformers
|
|
tags:
|
|
- mergekit
|
|
- merge
|
|
|
|
---
|
|
# Merge_Large_model_STock
|
|
New merge method with better results, in all aspects a improvement over the previous version.
|
|
At the core still focussed on large context, uncensored focussed on RP and story.
|
|
|
|
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 [Model Stock](https://arxiv.org/abs/2403.19522) merge method using \Llama-3-70B-Instruct-Gradient-262k as a base.
|
|
|
|
### Models Merged
|
|
|
|
The following models were included in the merge:
|
|
* \Llama-3-Giraffe-70B
|
|
* \Smaug-Llama-3-70B-Instruct
|
|
* \Llama3-70B-Chinese-Chat
|
|
* \Llama-3-Lumimaid-70B-v0.1-OAS
|
|
* \Higgs-Llama-3-70B
|
|
|
|
### Configuration
|
|
|
|
The following YAML configuration was used to produce this model:
|
|
|
|
```yaml
|
|
models:
|
|
- model: \Llama-3-70B-Instruct-Gradient-262k
|
|
- model: \Llama-3-Giraffe-70B
|
|
- model: \Llama3-70B-Chinese-Chat
|
|
- model: \Higgs-Llama-3-70B
|
|
- model: \Smaug-Llama-3-70B-Instruct
|
|
- model: \Llama-3-Lumimaid-70B-v0.1-OAS
|
|
merge_method: model_stock
|
|
base_model: \Llama-3-70B-Instruct-Gradient-262k
|
|
dtype: bfloat16
|
|
```
|
|
|
