56 lines
1.4 KiB
Markdown
56 lines
1.4 KiB
Markdown
---
|
|
base_model:
|
|
- meta-llama/Llama-2-13b-chat-hf
|
|
- wvnvwn/llama-2-13b-chat-hf-SSFT-lr5e-5
|
|
- wvnvwn/llama-2-13b-chat-hf-lr5e-5-gsm8k-lr5e-5
|
|
library_name: transformers
|
|
tags:
|
|
- mergekit
|
|
- merge
|
|
|
|
---
|
|
# resta_recovered_0.3
|
|
|
|
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 [linear](https://arxiv.org/abs/2203.05482) merge method.
|
|
|
|
### Models Merged
|
|
|
|
The following models were included in the merge:
|
|
* [meta-llama/Llama-2-13b-chat-hf](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf)
|
|
* [wvnvwn/llama-2-13b-chat-hf-SSFT-lr5e-5](https://huggingface.co/wvnvwn/llama-2-13b-chat-hf-SSFT-lr5e-5)
|
|
* [wvnvwn/llama-2-13b-chat-hf-lr5e-5-gsm8k-lr5e-5](https://huggingface.co/wvnvwn/llama-2-13b-chat-hf-lr5e-5-gsm8k-lr5e-5)
|
|
|
|
### Configuration
|
|
|
|
The following YAML configuration was used to produce this model:
|
|
|
|
```yaml
|
|
dtype: float16
|
|
merge_method: linear
|
|
slices:
|
|
- sources:
|
|
- layer_range: [0, 40]
|
|
model:
|
|
model:
|
|
path: wvnvwn/llama-2-13b-chat-hf-lr5e-5-gsm8k-lr5e-5
|
|
parameters:
|
|
weight: 1.0
|
|
- layer_range: [0, 40]
|
|
model:
|
|
model:
|
|
path: wvnvwn/llama-2-13b-chat-hf-SSFT-lr5e-5
|
|
parameters:
|
|
weight: 0.3
|
|
- layer_range: [0, 40]
|
|
model:
|
|
model:
|
|
path: meta-llama/Llama-2-13b-chat-hf
|
|
parameters:
|
|
weight: -0.3
|
|
```
|