Qwen
					Collection
				
Alibaba Cloud-based models
					• 
				2186 items
				• 
				Updated
					
				•
					
					5
This is a merge of pre-trained language models created using mergekit.
This model was merged using the TIES merge method using Qwen/Qwen2.5-14B-Instruct-1M as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
  - model: huihui-ai/Qwen2.5-14B-Instruct-1M-abliterated
    parameters:
      density: 1
      weight: 1
  - model: Qwen/Qwen2.5-14B-Instruct-1M
    parameters:
      density: 1
      weight: 1
merge_method: ties
base_model: Qwen/Qwen2.5-14B-Instruct-1M
parameters:
  normalize: false
  int8_mask: true
dtype: float16
Detailed results can be found here
| Metric | Value | 
|---|---|
| Avg. | 37.41 | 
| IFEval (0-Shot) | 59.86 | 
| BBH (3-Shot) | 47.26 | 
| MATH Lvl 5 (4-Shot) | 35.73 | 
| GPQA (0-shot) | 16.67 | 
| MuSR (0-shot) | 19.68 | 
| MMLU-PRO (5-shot) | 45.28 |