metadata
base_model:
- Qwen/Qwen2.5-Math-7B
- Qwen/Qwen2.5-7B-Instruct
library_name: transformers
tags:
- mergekit
- merge
Qwen2.5-7B-Instruct-Math-slerp
This is a merge of pre-trained language models created using mergekit.
Performance
| Metric | Value |
|---|---|
| GSM8k (zero-shot) | 91.05 |
| HellaSwag (zero-Shot) | 81.01 |
| MBPP (zero-shot) | 61.48 |
Merge Details
Merge Method
This model was merged using the SLERP merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
base_model: Qwen/Qwen2.5-7B-Instruct
dtype: bfloat16
merge_method: slerp
parameters:
t: 0.1
slices:
- sources:
- layer_range: [0, 28]
model: Qwen/Qwen2.5-7B-Instruct
- layer_range: [0, 28]
model: Qwen/Qwen2.5-Math-7B