|
--- |
|
base_model: |
|
- Qwen/QwQ-32B |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
|
|
--- |
|
# QwQ-32B Kumo |
|
|
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
merge_method: slerp |
|
base_model: Qwen/QwQ-32B |
|
models: |
|
- model: Qwen/QwQ-32B |
|
- model: NovaSky-AI/Sky-T1-32B-Flash |
|
parameters: |
|
t: 0.4 |
|
dtype: bfloat16 |
|
name: merge_model_1 |
|
--- |
|
merge_method: breadcrumbs_ties |
|
base_model: Qwen/QwQ-32B |
|
tokenizer_source: Qwen/QwQ-32B |
|
name: merge_model_2 |
|
models: |
|
- model: Qwen/QwQ-32B |
|
parameters: |
|
weight: 1.0 |
|
- model: FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview |
|
parameters: |
|
weight: 0.75 |
|
dtype: bfloat16 |
|
--- |
|
merge_method: task_arithmetic |
|
base_model: Qwen/Qwen2.5-32B |
|
tokenizer_source: Qwen/QwQ-32B |
|
name: merge_model_3 |
|
models: |
|
- model: rinna/deepseek-r1-distill-qwen2.5-bakeneko-32b |
|
parameters: |
|
weight: 1.0 |
|
- model: cyberagent/DeepSeek-R1-Distill-Qwen-32B-Japanese |
|
parameters: |
|
weight: 0.9 |
|
tokenizer_source: base |
|
dtype: bfloat16 |
|
--- |
|
merge_method: slerp |
|
base_model: Qwen/QwQ-32B |
|
models: |
|
- model: Qwen/QwQ-32B |
|
- model: TeamDelta/ABEJA-Qwen2.5-32B-base-jp-v0.1 |
|
parameters: |
|
t: 0.5 |
|
tokenizer_source: base |
|
dtype: bfloat16 |
|
name: merge_model_4 |
|
--- |
|
merge_method: model_stock |
|
|
|
base_model: Qwen/QwQ-32B |
|
|
|
models: |
|
- model: Qwen/QwQ-32B |
|
- model: merge_model_1 |
|
- model: merge_model_2 |
|
- model: merge_model_3 |
|
- model: merge_model_4 |
|
|
|
dtype: bfloat16 |
|
|
|
pad_to_multiple_of: 512 |
|
tokenizer_source: base |
|
|
|
name: QwQ-32B-Kumo |
|
``` |
|
|
