q3-30b-rc1 / README.md
Fizzarolli's picture
Update README.md
2c53990 verified
---
base_model:
- Qwen/Qwen3-30B-A3B-Base
- allura-forge/q3-30b-ft-ep2-merged
- Qwen/Qwen3-30B-A3B
- Gryphe/Pantheon-Proto-RP-1.8-30B-A3B
library_name: transformers
tags:
- mergekit
- merge
---
# Please see [Pentiment](https://huggingface.co/allura-org/Q3-30b-A3b-Pentiment) for the final result of this merge
# output
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [SCE](https://arxiv.org/abs/2408.07990) merge method using [Qwen/Qwen3-30B-A3B-Base](https://huggingface.co/Qwen/Qwen3-30B-A3B-Base) as a base.
### Models Merged
The following models were included in the merge:
* [allura-forge/q3-30b-ft-ep2-merged](https://huggingface.co/allura-forge/q3-30b-ft-ep2-merged)
* [Qwen/Qwen3-30B-A3B](https://huggingface.co/Qwen/Qwen3-30B-A3B)
* [Gryphe/Pantheon-Proto-RP-1.8-30B-A3B](https://huggingface.co/Gryphe/Pantheon-Proto-RP-1.8-30B-A3B)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
base_model: Qwen/Qwen3-30B-A3B-Base
models:
- model: allura-forge/q3-30b-ft-ep2-merged
parameters:
select_topk: 0.75
- model: Gryphe/Pantheon-Proto-RP-1.8-30B-A3B
parameters:
select_topk: 0.4
- model: Qwen/Qwen3-30B-A3B
parameters:
select_topk: 0.25
merge_method: sce
dtype: bfloat16
```