metadata
base_model:
- FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview
- Qwen/Qwen2.5-Coder-32B
- rombodawg/Rombos-Coder-V2.5-Qwen-32b
library_name: transformers
tags:
- mergekit
- merge
RambO1-Fuse
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the sce merge method using Qwen/Qwen2.5-Coder-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:
base_model: Qwen/Qwen2.5-Coder-32B
dtype: bfloat16
merge_method: sce
parameters:
select_topk: 1.0
slices:
- sources:
- layer_range: [0, 64]
model: rombodawg/Rombos-Coder-V2.5-Qwen-32b
- layer_range: [0, 64]
model: FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview
- layer_range: [0, 64]
model: Qwen/Qwen2.5-Coder-32B