metadata
base_model:
- Qwen/Qwen2.5-32B
- Qwen/QwQ-32B-Preview
- unsloth/DeepSeek-R1-Distill-Qwen-32B
library_name: transformers
tags:
- mergekit
- merge
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the TIES merge method using Qwen/Qwen2.5-32B as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
models:
- model: unsloth/DeepSeek-R1-Distill-Qwen-32B
parameters:
weight: 0.65
density: 0.65
- model: Qwen/QwQ-32B-Preview
parameters:
weight: 0.35
density: 0.35
merge_method: ties
base_model: Qwen/Qwen2.5-32B
parameters:
normalize: true
int8_mask: true
tokenizer_source: "unsloth/DeepSeek-R1-Distill-Qwen-32B"
dtype: float16