51 lines
1.6 KiB
Markdown
51 lines
1.6 KiB
Markdown
|
---
|
||
|
|
base_model:
|
||
|
|
- ontocord/wide_3b_sft_stage1.2-ss1-expert_math
|
||
|
|
- ontocord/wide_3b_sft_stage1.2-ss1-expert_fictional_lyrical
|
||
|
|
- ontocord/wide_3b_sft_stage1.1-ss1-with_generics_intr_math_stories.no_issue
|
||
|
|
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 [TIES](https://arxiv.org/abs/2306.01708) merge method using [ontocord/wide_3b_sft_stage1.1-ss1-with_generics_intr_math_stories.no_issue](https://huggingface.co/ontocord/wide_3b_sft_stage1.1-ss1-with_generics_intr_math_stories.no_issue) as a base.
|
||
|
|
|
||
|
|
### Models Merged
|
||
|
|
|
||
|
|
The following models were included in the merge:
|
||
|
|
* [ontocord/wide_3b_sft_stage1.2-ss1-expert_math](https://huggingface.co/ontocord/wide_3b_sft_stage1.2-ss1-expert_math)
|
||
|
|
* [ontocord/wide_3b_sft_stage1.2-ss1-expert_fictional_lyrical](https://huggingface.co/ontocord/wide_3b_sft_stage1.2-ss1-expert_fictional_lyrical)
|
||
|
|
|
||
|
|
### Configuration
|
||
|
|
|
||
|
|
The following YAML configuration was used to produce this model:
|
||
|
|
|
||
|
|
```yaml
|
||
|
|
models:
|
||
|
|
- model: ontocord/wide_3b_sft_stage1.1-ss1-with_generics_intr_math_stories.no_issue
|
||
|
|
#no parameters necessary for base model
|
||
|
|
- model: ontocord/wide_3b_sft_stage1.2-ss1-expert_math
|
||
|
|
parameters:
|
||
|
|
density: 0.5
|
||
|
|
weight: 0.5
|
||
|
|
- model: ontocord/wide_3b_sft_stage1.2-ss1-expert_fictional_lyrical
|
||
|
|
parameters:
|
||
|
|
density: 0.5
|
||
|
|
weight: 0.5
|
||
|
|
|
||
|
|
merge_method: ties
|
||
|
|
base_model: ontocord/wide_3b_sft_stage1.1-ss1-with_generics_intr_math_stories.no_issue
|
||
|
|
parameters:
|
||
|
|
normalize: false
|
||
|
|
int8_mask: true
|
||
|
|
dtype: float16
|
||
|
|
```
|