|
--- |
|
base_model: |
|
- Qwen/Qwen2.5-14B-Instruct |
|
- Lambent/alternate-instruct-qwen2.5-14B |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
|
|
--- |
|
# qwenselfinstructalt |
|
|
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). |
|
|
|
## Merge Details |
|
|
|
Same idea as Lambent/qwen2.5-14B-selfmerge-A, but training the base model on an ~20M token instruct and continued pretraining dataset first. |
|
|
|
Hope is the lightweight instruction tuning might add some synergy with the original instruct. |
|
|
|
Testing: eq-bench showed no syntax errors and result was 75.6984, closer to original instruct value of 76.9195 than selfmerge-A (which had 73.8068). |
|
|
|
Subsets of mrfakename/Capybara-ShareGPT, abacusai/SystemChat-1.1, anthracite-org/nopm_claude_writing_fixed and fineweb-edu were used for the alternate training. |
|
|
|
### Merge Method |
|
|
|
This model was merged using the SLERP merge method. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct) |
|
* [Lambent/alternate-instruct-qwen2.5-14B](https://huggingface.co/Lambent/alternate-instruct-qwen2.5-14B) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
models: |
|
- model: Lambent/alternate-instruct-qwen2.5-14B |
|
merge_method: slerp |
|
base_model: Qwen/Qwen2.5-14B-Instruct |
|
parameters: |
|
t: |
|
- value: [0, 0, 0.3, 0.4, 0.5, 0.6, 0.5, 0.4, 0.3, 0, 0] |
|
dtype: bfloat16 |
|
|
|
|
|
``` |
|
|
