|
|
--- |
|
|
base_model: |
|
|
- Qwen/Qwen2.5-Coder-32B-Instruct |
|
|
- NovaSky-AI/Sky-T1-32B-Flash |
|
|
- Qwen/Qwen2.5-Coder-32B |
|
|
library_name: transformers |
|
|
tags: |
|
|
- mergekit |
|
|
- merge |
|
|
- qwen2 |
|
|
license: apache-2.0 |
|
|
--- |
|
|
# merge |
|
|
|
|
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). |
|
|
|
|
|
I wanted to see if it would be possible to improve on [FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview](https://huggingface.co/FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview) and [CoderO1-DeepSeekR1-Coder-32B-Preview](https://huggingface.co/RDson/CoderO1-DeepSeekR1-Coder-32B-Preview) by using [Sky-T1-32B-Flash](https://huggingface.co/NovaSky-AI/Sky-T1-32B-Flash) as the reasoning model that is merged with [Qwen2.5-Coder-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct) instead of DeepSeek-R1-Distill-Qwen-32B. The idea is to have a strong coder model that can reason but without very long reasoning chains (hence using the Flash model). |
|
|
|
|
|
## Merge Details |
|
|
### Merge Method |
|
|
|
|
|
This model was merged using the [SCE](https://arxiv.org/abs/2408.07990) merge method using [Qwen/Qwen2.5-Coder-32B](https://huggingface.co/Qwen/Qwen2.5-Coder-32B) as a base. |
|
|
|
|
|
### Models Merged |
|
|
|
|
|
The following models were included in the merge: |
|
|
* [Qwen/Qwen2.5-Coder-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct) |
|
|
* [NovaSky-AI/Sky-T1-32B-Flash](https://huggingface.co/NovaSky-AI/Sky-T1-32B-Flash) |
|
|
|
|
|
### Configuration |
|
|
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
|
|
```yaml |
|
|
models: |
|
|
# Pivot model |
|
|
- model: Qwen/Qwen2.5-Coder-32B |
|
|
# Target models |
|
|
- model: Qwen/Qwen2.5-Coder-32B-Instruct |
|
|
- model: NovaSky-AI/Sky-T1-32B-Flash |
|
|
merge_method: sce |
|
|
base_model: Qwen/Qwen2.5-Coder-32B |
|
|
parameters: |
|
|
select_topk: 1.0 |
|
|
dtype: bfloat16 |
|
|
``` |
