|
|
---
|
|
|
base_model:
|
|
|
- deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
|
|
|
- Qwen/QwQ-32B
|
|
|
- Qwen/Qwen2.5-Coder-32B-Instruct
|
|
|
- Qwen/Qwen2.5-32B
|
|
|
library_name: transformers
|
|
|
tags:
|
|
|
- mergekit
|
|
|
- merge
|
|
|
language:
|
|
|
- zho
|
|
|
- eng
|
|
|
- fra
|
|
|
- spa
|
|
|
- por
|
|
|
- deu
|
|
|
- ita
|
|
|
- rus
|
|
|
- jpn
|
|
|
- kor
|
|
|
- vie
|
|
|
- tha
|
|
|
- ara
|
|
|
---
|
|
|
# tomasmcm/QwQ-Coder-R1-Distill-32B
|
|
|
|
|
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
|
|
|
|
|
Following up on [tomasmcm/sky-t1-coder-32b-flash](https://huggingface.co/tomasmcm/sky-t1-coder-32b-flash), this experiment tries to merge 2 reasoning models based on Qwen 32B with a Coder model. But it seems to have caused the model to loose it's thinking abilities, even when adding `<think>` to the prompt.
|
|
|
|
|
|
|
|
|
## Merge Details
|
|
|
### Merge Method
|
|
|
|
|
|
This model was merged using the [SCE](https://arxiv.org/abs/2408.07990) merge method using [Qwen/Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B) as a base.
|
|
|
|
|
|
### Models Merged
|
|
|
|
|
|
The following models were included in the merge:
|
|
|
* [deepseek-ai/DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B)
|
|
|
* [Qwen/QwQ-32B](https://huggingface.co/Qwen/QwQ-32B)
|
|
|
* [Qwen/Qwen2.5-Coder-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct)
|
|
|
|
|
|
### Configuration
|
|
|
|
|
|
The following YAML configuration was used to produce this model:
|
|
|
|
|
|
```yaml
|
|
|
models:
|
|
|
# Pivot model
|
|
|
- model: Qwen/Qwen2.5-32B
|
|
|
# Target models
|
|
|
- model: Qwen/Qwen2.5-Coder-32B-Instruct
|
|
|
- model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
|
|
|
- model: Qwen/QwQ-32B
|
|
|
merge_method: sce
|
|
|
base_model: Qwen/Qwen2.5-32B
|
|
|
parameters:
|
|
|
select_topk: 1.0
|
|
|
dtype: bfloat16
|
|
|
|
|
|
```
|
|
|
|
