merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the Model Stock merge method using ZeroXClem/Qwen-2.5-Aether-SlerpFusion-7B + bunnycore/Qwen-2.5-7b-rp-lora as a base.
Models Merged
The following models were included in the merge:
- bespokelabs/Bespoke-Stratos-7B
- Sakalti/light-7b-beta
- ZeroXClem/Qwen-2.5-Aether-SlerpFusion-7B
- deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
- fblgit/cybertron-v4-qw7B-MGS + bunnycore/Qwen-2.5-7b-rp-lora
Configuration
The following YAML configuration was used to produce this model:
merge_method: model_stock
base_model: ZeroXClem/Qwen-2.5-Aether-SlerpFusion-7B+bunnycore/Qwen-2.5-7b-rp-lora
tokenizer_source: base
dtype: float32
out_dtype: bfloat16
parameters:
int8_mask: true
normalize: true
rescale: false
models:
- model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
- model: ZeroXClem/Qwen-2.5-Aether-SlerpFusion-7B
- model: ZeroXClem/Qwen-2.5-Aether-SlerpFusion-7B+bunnycore/Qwen-2.5-7b-rp-lora
- model: Sakalti/light-7b-beta
- model: fblgit/cybertron-v4-qw7B-MGS+bunnycore/Qwen-2.5-7b-rp-lora
- model: bespokelabs/Bespoke-Stratos-7B
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 27.38 |
| IFEval (0-Shot) | 56.95 |
| BBH (3-Shot) | 34.08 |
| MATH Lvl 5 (4-Shot) | 25.53 |
| GPQA (0-shot) | 3.69 |
| MuSR (0-shot) | 9.96 |
| MMLU-PRO (5-shot) | 34.06 |