|
--- |
|
base_model: |
|
- arcee-ai/Virtuoso-Medium-v2 |
|
- crestf411/Q2.5-32B-Slush |
|
- nbeerbower/Dumpling-Qwen2.5-32B |
|
- maldv/Qwenstein2.5-32B-Instruct |
|
- allura-org/Qwen2.5-32b-RP-Ink |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
|
|
--- |
|
# merge |
|
|
|
It's noticeably better than Q2.5-Qwetiapin-32B, but I'll leave it as is until arcee-ai releases a 32B R1 distill. (If that will happen though) |
|
|
|
## Merge Details |
|
### Merge Method |
|
|
|
This model was merged using the [Model Breadcrumbs with TIES](https://arxiv.org/abs/2312.06795) merge method using [arcee-ai/Virtuoso-Medium-v2](https://huggingface.co/arcee-ai/Virtuoso-Medium-v2) as a base. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [crestf411/Q2.5-32B-Slush](https://huggingface.co/crestf411/Q2.5-32B-Slush) |
|
* [nbeerbower/Dumpling-Qwen2.5-32B](https://huggingface.co/nbeerbower/Dumpling-Qwen2.5-32B) |
|
* [maldv/Qwenstein2.5-32B-Instruct](https://huggingface.co/maldv/Qwenstein2.5-32B-Instruct) |
|
* [allura-org/Qwen2.5-32b-RP-Ink](https://huggingface.co/allura-org/Qwen2.5-32b-RP-Ink) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
models: |
|
- model: arcee-ai/Virtuoso-Medium-v2 |
|
- model: maldv/Qwenstein2.5-32B-Instruct |
|
parameters: |
|
density: 0.5 |
|
weight: 0.4 |
|
gamma: 0.03 |
|
- model: allura-org/Qwen2.5-32b-RP-Ink |
|
parameters: |
|
density: 0.77 |
|
gamma: 0.007 |
|
weight: 0.07 |
|
- model: nbeerbower/Dumpling-Qwen2.5-32B |
|
parameters: |
|
density: 0.88 |
|
gamma: 0.008 |
|
weight: 0.28 |
|
- model: crestf411/Q2.5-32B-Slush |
|
parameters: |
|
density: 0.75 |
|
gamma: 0.01 |
|
weight: 0.05 |
|
base_model: arcee-ai/Virtuoso-Medium-v2 |
|
merge_method: breadcrumbs_ties |
|
parameters: |
|
int8_mask: true |
|
rescale: true |
|
normalize: true |
|
dtype: bfloat16 |
|
tokenizer_source: base |
|
``` |
|
|
