Qwen
Collection
Alibaba Cloud-based models
•
1246 items
•
Updated
•
5
This is a merge of pre-trained language models created using mergekit.
We're all stories in the end
This model was merged using the TIES merge method using v000000/Qwen2.5-Lumen-14B as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: v000000/Qwen2.5-Lumen-14B
#no parameters necessary for base model
- model: Qwen/Qwen2.5-Coder-14B
parameters:
density: 0.5
weight: 0.5
- model: Krystalan/DRT-o1-14B
parameters:
density: 0.5
weight: 0.5
merge_method: ties
base_model: v000000/Qwen2.5-Lumen-14B
parameters:
normalize: false
int8_mask: true
dtype: float16
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 4.56 |
IFEval (0-Shot) | 18.79 |
BBH (3-Shot) | 2.95 |
MATH Lvl 5 (4-Shot) | 0.00 |
GPQA (0-shot) | 0.00 |
MuSR (0-shot) | 3.81 |
MMLU-PRO (5-shot) | 1.83 |