|
---
|
|
base_model:
|
|
- grimjim/kukulemon-32K-7B
|
|
- grimjim/rogue-enchantress-32k-7B
|
|
library_name: transformers
|
|
tags:
|
|
- mergekit
|
|
- merge
|
|
license: cc-by-nc-4.0
|
|
pipeline_tag: text-generation
|
|
---
|
|
# kukulemon-v3-soul_mix-32k-7B
|
|
|
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
|
|
|
We explore merger at extremely low weight as an alternative to fine-tuning. The additional model was applied at a weight of 10e-5, which was selected to be comparable to a few epochs of training. The low weight also amounts to the additional model being flattened, though technically not sparsified.
|
|
|
|
- [Full weights](https://huggingface.co/grimjim/kukulemon-v3-soul_mix-32k-7B)
|
|
- [GGUF quants](https://huggingface.co/grimjim/kukulemon-v3-soul_mix-32k-7B-GGUF)
|
|
|
|
## Merge Details
|
|
### Merge Method
|
|
|
|
This model was merged using the [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using [grimjim/kukulemon-32K-7B](https://huggingface.co/grimjim/kukulemon-32K-7B) as a base.
|
|
|
|
### Models Merged
|
|
|
|
The following model was included in the merge:
|
|
* [grimjim/rogue-enchantress-32k-7B](https://huggingface.co/grimjim/rogue-enchantress-32k-7B)
|
|
|
|
### Configuration
|
|
|
|
The following YAML configuration was used to produce this model:
|
|
|
|
```yaml
|
|
base_model: grimjim/kukulemon-32K-7B
|
|
dtype: bfloat16
|
|
merge_method: task_arithmetic
|
|
slices:
|
|
- sources:
|
|
- layer_range: [0, 32]
|
|
model: grimjim/kukulemon-32K-7B
|
|
- layer_range: [0, 32]
|
|
model: grimjim/rogue-enchantress-32k-7B
|
|
parameters:
|
|
weight: 10e-5
|
|
|
|
```
|
|
|
