|
--- |
|
base_model: |
|
- nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B |
|
- mistralai/Mistral-Nemo-Base-2407 |
|
- nbeerbower/Lyra-Gutenberg-mistral-nemo-12B |
|
- nbeerbower/mistral-nemo-bophades-12B |
|
- HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407 |
|
- mergekit-community/MN-Sappho-g3-12B |
|
- Nitral-AI/Captain-Eris_Violet-GRPO-v0.420 |
|
- mergekit-community/MN-Hekate-Daidalos-17B |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
|
|
--- |
|
# merge |
|
|
|
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 [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [mergekit-community/MN-Hekate-Daidalos-17B](https://huggingface.co/mergekit-community/MN-Hekate-Daidalos-17B) as a base. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B](https://huggingface.co/nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B) |
|
* [mistralai/Mistral-Nemo-Base-2407](https://huggingface.co/mistralai/Mistral-Nemo-Base-2407) |
|
* [nbeerbower/Lyra-Gutenberg-mistral-nemo-12B](https://huggingface.co/nbeerbower/Lyra-Gutenberg-mistral-nemo-12B) |
|
* [nbeerbower/mistral-nemo-bophades-12B](https://huggingface.co/nbeerbower/mistral-nemo-bophades-12B) |
|
* [HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407](https://huggingface.co/HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407) |
|
* [mergekit-community/MN-Sappho-g3-12B](https://huggingface.co/mergekit-community/MN-Sappho-g3-12B) |
|
* [Nitral-AI/Captain-Eris_Violet-GRPO-v0.420](https://huggingface.co/Nitral-AI/Captain-Eris_Violet-GRPO-v0.420) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
dtype: float32 |
|
out_dtype: bfloat16 |
|
merge_method: model_stock |
|
base_model: mergekit-community/MN-Hekate-Daidalos-17B |
|
slices: |
|
- sources: |
|
- model: mergekit-community/MN-Hekate-Daidalos-17B |
|
layer_range: [0, 20] |
|
|
|
- sources: |
|
- model: mergekit-community/MN-Hekate-Daidalos-17B |
|
layer_range: [20, 36] |
|
parameters: |
|
weight: 3 |
|
- model: mistralai/Mistral-Nemo-Base-2407 |
|
layer_range: [16, 32] |
|
parameters: |
|
weight: 2 |
|
- model: Nitral-AI/Captain-Eris_Violet-GRPO-v0.420 |
|
layer_range: [16, 32] |
|
parameters: |
|
weight: [1.5, 1.49, 1.46, 1.4, 1.33, 1.25, 1.15, 1.05, 1] |
|
- model: nbeerbower/mistral-nemo-bophades-12B |
|
layer_range: [16, 32] |
|
parameters: |
|
weight: [1.5, 1.49, 1.46, 1.4, 1.33, 1.25, 1.15, 1.05, 1] |
|
- model: mergekit-community/MN-Sappho-g3-12B |
|
layer_range: [16, 32] |
|
parameters: |
|
weight: [1.0, 1.1, 1.2, 1.29, 1.37, 1.43, 1.48, 1.5, 1.5] |
|
- model: nbeerbower/Lyra-Gutenberg-mistral-nemo-12B |
|
layer_range: [16, 32] |
|
parameters: |
|
weight: [1.0, 1.1, 1.2, 1.29, 1.37, 1.43, 1.48, 1.5, 1.5] |
|
|
|
- sources: |
|
- model: mergekit-community/MN-Hekate-Daidalos-17B |
|
layer_range: [36, 56] |
|
parameters: |
|
weight: 3 |
|
- model: nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B |
|
layer_range: [20, 40] |
|
parameters: |
|
weight: [1, 0.75] |
|
- model: Nitral-AI/Captain-Eris_Violet-GRPO-v0.420 |
|
layer_range: [20, 40] |
|
parameters: |
|
weight: [1, 0.5] |
|
- model: HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407 |
|
layer_range: [20, 40] |
|
parameters: |
|
weight: [1, 0.75] |
|
|
|
tokenizer: |
|
source: union |
|
tokens: |
|
"[INST]": |
|
source: mergekit-community/MN-Hekate-Daidalos-17B |
|
force: true |
|
"[/INST]": |
|
source: mergekit-community/MN-Hekate-Daidalos-17B |
|
force: true |
|
"<|im_start|>": |
|
source: mergekit-community/MN-Hekate-Daidalos-17B |
|
force: true |
|
"<|im_end|>": |
|
source: mergekit-community/MN-Hekate-Daidalos-17B |
|
force: true |
|
|
|
``` |
|
|