|
--- |
|
base_model: |
|
- mistralai/Codestral-22B-v0.1 |
|
- nvidia/Mistral-NeMo-Minitron-8B-Instruct |
|
- mistralai/Mistral-Large-Instruct-2407 |
|
- mistralai/Mistral-Nemo-Base-2407 |
|
- mistralai/Mathstral-7B-v0.1 |
|
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 passthrough merge method. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [mistralai/Codestral-22B-v0.1](https://huggingface.co/mistralai/Codestral-22B-v0.1) |
|
* [nvidia/Mistral-NeMo-Minitron-8B-Instruct](https://huggingface.co/nvidia/Mistral-NeMo-Minitron-8B-Instruct) |
|
* [mistralai/Mistral-Large-Instruct-2407](https://huggingface.co/mistralai/Mistral-Large-Instruct-2407) |
|
* [mistralai/Mistral-Nemo-Base-2407](https://huggingface.co/mistralai/Mistral-Nemo-Base-2407) |
|
* [mistralai/Mathstral-7B-v0.1](https://huggingface.co/mistralai/Mathstral-7B-v0.1) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
dtype: float16 |
|
merge_method: passthrough |
|
slices: |
|
- sources: |
|
- layer_range: [0, 8] |
|
model: mistralai/Mistral-Large-Instruct-2407 |
|
- sources: |
|
- layer_range: [4, 12] |
|
model: nvidia/Mistral-NeMo-Minitron-8B-Instruct |
|
- sources: |
|
- layer_range: [8, 16] |
|
model: mistralai/Mistral-Nemo-Base-2407 |
|
- sources: |
|
- layer_range: [12, 20] |
|
model: mistralai/Codestral-22B-v0.1 |
|
- sources: |
|
- layer_range: [16, 24] |
|
model: mistralai/Mathstral-7B-v0.1 |
|
|
|
``` |
|
|
