|
--- |
|
base_model: [] |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
|
|
--- |
|
# toppy_old_remake |
|
|
|
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 [Task Arithmetic](https://arxiv.org/abs/2212.04089) merge method using /workspace/toppy/mistralai_Mistral-7B-v0.1 as a base. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* /workspace/toppy/stepB1 |
|
* /workspace/toppy/stepC1 |
|
* /workspace/toppy/stepA1 |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
base_model: /workspace/toppy/mistralai_Mistral-7B-v0.1 |
|
dtype: bfloat16 |
|
merge_method: task_arithmetic |
|
modules: |
|
default: |
|
slices: |
|
- sources: |
|
- layer_range: [0, 8] |
|
model: /workspace/toppy/stepC1 |
|
parameters: |
|
weight: -0.08064321988635652 |
|
- layer_range: [0, 8] |
|
model: /workspace/toppy/stepB1 |
|
parameters: |
|
weight: 0.47180144787421097 |
|
- layer_range: [0, 8] |
|
model: /workspace/toppy/stepA1 |
|
parameters: |
|
weight: 0.49216900949431464 |
|
- layer_range: [0, 8] |
|
model: /workspace/toppy/mistralai_Mistral-7B-v0.1 |
|
- sources: |
|
- layer_range: [8, 16] |
|
model: /workspace/toppy/stepC1 |
|
parameters: |
|
weight: 0.4262113662158592 |
|
- layer_range: [8, 16] |
|
model: /workspace/toppy/stepB1 |
|
parameters: |
|
weight: 0.25821032498583896 |
|
- layer_range: [8, 16] |
|
model: /workspace/toppy/stepA1 |
|
parameters: |
|
weight: 1.1337184135136393 |
|
- layer_range: [8, 16] |
|
model: /workspace/toppy/mistralai_Mistral-7B-v0.1 |
|
- sources: |
|
- layer_range: [16, 24] |
|
model: /workspace/toppy/stepC1 |
|
parameters: |
|
weight: 0.08816883209543347 |
|
- layer_range: [16, 24] |
|
model: /workspace/toppy/stepB1 |
|
parameters: |
|
weight: -0.04615180476355138 |
|
- layer_range: [16, 24] |
|
model: /workspace/toppy/stepA1 |
|
parameters: |
|
weight: 0.6614915110635577 |
|
- layer_range: [16, 24] |
|
model: /workspace/toppy/mistralai_Mistral-7B-v0.1 |
|
- sources: |
|
- layer_range: [24, 32] |
|
model: /workspace/toppy/stepC1 |
|
parameters: |
|
weight: 0.2995904282557765 |
|
- layer_range: [24, 32] |
|
model: /workspace/toppy/stepB1 |
|
parameters: |
|
weight: 0.48755088752753767 |
|
- layer_range: [24, 32] |
|
model: /workspace/toppy/stepA1 |
|
parameters: |
|
weight: 0.48445653643927594 |
|
- layer_range: [24, 32] |
|
model: /workspace/toppy/mistralai_Mistral-7B-v0.1 |
|
parameters: |
|
int8_mask: 1.0 |
|
normalize: 0.0 |
|
tokenizer_source: /workspace/toppy/stepC1 |
|
``` |
|
|