50 lines
1.2 KiB
Markdown
50 lines
1.2 KiB
Markdown
|
---
|
||
|
|
base_model:
|
||
|
|
- Qwen/Qwen2.5-1.5B-Instruct
|
||
|
|
- Athkal/model-sft-lora
|
||
|
|
library_name: transformers
|
||
|
|
tags:
|
||
|
|
- mergekit
|
||
|
|
- merge
|
||
|
|
|
||
|
|
---
|
||
|
|
# model_sft_resta
|
||
|
|
|
||
|
|
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 [Task Arithmetic](https://arxiv.org/abs/2212.04089) merge method using [Athkal/model-sft-lora](https://huggingface.co/Athkal/model-sft-lora) as a base.
|
||
|
|
|
||
|
|
### Models Merged
|
||
|
|
|
||
|
|
The following models were included in the merge:
|
||
|
|
* /kaggle/working/model_harmful_lora
|
||
|
|
* [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct)
|
||
|
|
|
||
|
|
### Configuration
|
||
|
|
|
||
|
|
The following YAML configuration was used to produce this model:
|
||
|
|
|
||
|
|
```yaml
|
||
|
|
base_model: Athkal/model-sft-lora
|
||
|
|
dtype: float16
|
||
|
|
merge_method: task_arithmetic
|
||
|
|
modules:
|
||
|
|
default:
|
||
|
|
slices:
|
||
|
|
- sources:
|
||
|
|
- layer_range: [0, 28]
|
||
|
|
model: Qwen/Qwen2.5-1.5B-Instruct
|
||
|
|
parameters:
|
||
|
|
weight: 1.0
|
||
|
|
- layer_range: [0, 28]
|
||
|
|
model: /kaggle/working/model_harmful_lora
|
||
|
|
parameters:
|
||
|
|
weight: -1.0
|
||
|
|
- layer_range: [0, 28]
|
||
|
|
model: Athkal/model-sft-lora
|
||
|
|
tokenizer_source: base
|
||
|
|
```
|