|
|
--- |
|
|
base_model: |
|
|
- PocketDoc/Dans-PersonalityEngine-V1.2.0-24b |
|
|
- lars1234/Mistral-Small-24B-Instruct-2501-writer |
|
|
- mistralai/Mistral-Small-24B-Instruct-2501 |
|
|
- trashpanda-org/Llama3-24B-Mullein-v1 |
|
|
- unsloth/Mistral-Small-24B-Base-2501 |
|
|
- arcee-ai/Arcee-Blitz |
|
|
- allura-org/Mistral-Small-24b-Sertraline-0304 |
|
|
library_name: transformers |
|
|
tags: |
|
|
- mergekit |
|
|
- mergekitty |
|
|
- merge |
|
|
|
|
|
--- |
|
|
# v0a |
|
|
|
|
|
This is a merge of pre-trained language models created using [mergekitty](https://github.com/allura-org/mergekitty). |
|
|
|
|
|
## Merge Details |
|
|
### Merge Method |
|
|
|
|
|
This model was merged using the [SCE](https://arxiv.org/abs/2408.07990) merge method using [unsloth/Mistral-Small-24B-Base-2501](https://huggingface.co/unsloth/Mistral-Small-24B-Base-2501) as a base. |
|
|
|
|
|
### Models Merged |
|
|
|
|
|
The following models were included in the merge: |
|
|
* [PocketDoc/Dans-PersonalityEngine-V1.2.0-24b](https://huggingface.co/PocketDoc/Dans-PersonalityEngine-V1.2.0-24b) |
|
|
* [lars1234/Mistral-Small-24B-Instruct-2501-writer](https://huggingface.co/lars1234/Mistral-Small-24B-Instruct-2501-writer) |
|
|
* [mistralai/Mistral-Small-24B-Instruct-2501](https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501) |
|
|
* [trashpanda-org/Llama3-24B-Mullein-v1](https://huggingface.co/trashpanda-org/Llama3-24B-Mullein-v1) |
|
|
* [arcee-ai/Arcee-Blitz](https://huggingface.co/arcee-ai/Arcee-Blitz) |
|
|
* [allura-org/Mistral-Small-24b-Sertraline-0304](https://huggingface.co/allura-org/Mistral-Small-24b-Sertraline-0304) |
|
|
|
|
|
### Configuration |
|
|
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
|
|
```yaml |
|
|
base_model: unsloth/Mistral-Small-24B-Base-2501 |
|
|
merge_method: sce |
|
|
dtype: float32 |
|
|
out_dtype: bfloat16 |
|
|
models: |
|
|
- model: allura-org/Mistral-Small-24b-Sertraline-0304 |
|
|
parameters: |
|
|
select_topk: 0.50 |
|
|
- model: lars1234/Mistral-Small-24B-Instruct-2501-writer |
|
|
parameters: |
|
|
select_topk: 0.20 |
|
|
- model: PocketDoc/Dans-PersonalityEngine-V1.2.0-24b |
|
|
parameters: |
|
|
select_topk: 0.20 |
|
|
- model: trashpanda-org/Llama3-24B-Mullein-v1 |
|
|
parameters: |
|
|
select_topk: 0.175 |
|
|
- model: arcee-ai/Arcee-Blitz |
|
|
parameters: |
|
|
select_topk: 0.15 |
|
|
- model: mistralai/Mistral-Small-24B-Instruct-2501 |
|
|
parameters: |
|
|
select_topk: 0.15 |
|
|
|
|
|
# apt install git nano -y |
|
|
# uv tool install mergekitty --with hf_transfer |
|
|
# uv tool install https://github.com/aphrodite-engine/aphrodite-engine/releases/download/v0.6.7/aphrodite_engine-0.6.7-cp38-abi3-manylinux1_x86_64.whl --with aphrodite-engine --with setuptools --with hf_transfer |
|
|
# uv tool install huggingface_hub |
|
|
# huggingface-cli login |
|
|
# nano merge.yml |
|
|
# mergekitty-yaml --cuda --lazy-unpickle merge.yml v0a |
|
|
|
|
|
``` |
|
|
|
