|
--- |
|
base_model: [] |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
|
|
--- |
|
# final_merge_biomistral_e57b_tydien |
|
|
|
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 [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using ./evol_merge_storage_biomistral_e57b_tydien/input_models/e5-mistral-7b-instruct_2385958088 as a base. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* ./evol_merge_storage_biomistral_e57b_tydien/input_models/BioMistral-7B_3601864449 |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
base_model: ./evol_merge_storage_biomistral_e57b_tydien/input_models/e5-mistral-7b-instruct_2385958088 |
|
dtype: bfloat16 |
|
merge_method: dare_ties |
|
parameters: |
|
int8_mask: 1.0 |
|
normalize: 1.0 |
|
slices: |
|
- sources: |
|
- layer_range: [0, 4] |
|
model: ./evol_merge_storage_biomistral_e57b_tydien/input_models/e5-mistral-7b-instruct_2385958088 |
|
parameters: |
|
density: 0.8367579275276175 |
|
weight: 0.4706008624766047 |
|
- layer_range: [0, 4] |
|
model: ./evol_merge_storage_biomistral_e57b_tydien/input_models/BioMistral-7B_3601864449 |
|
parameters: |
|
density: 0.6199244761272209 |
|
weight: 0.49607199958757875 |
|
- sources: |
|
- layer_range: [4, 8] |
|
model: ./evol_merge_storage_biomistral_e57b_tydien/input_models/e5-mistral-7b-instruct_2385958088 |
|
parameters: |
|
density: 0.6844013361793727 |
|
weight: 0.35766754240777654 |
|
- layer_range: [4, 8] |
|
model: ./evol_merge_storage_biomistral_e57b_tydien/input_models/BioMistral-7B_3601864449 |
|
parameters: |
|
density: 0.8139831864708157 |
|
weight: 0.5914251642547961 |
|
- sources: |
|
- layer_range: [8, 12] |
|
model: ./evol_merge_storage_biomistral_e57b_tydien/input_models/e5-mistral-7b-instruct_2385958088 |
|
parameters: |
|
density: 1.0 |
|
weight: 0.8624665482114445 |
|
- layer_range: [8, 12] |
|
model: ./evol_merge_storage_biomistral_e57b_tydien/input_models/BioMistral-7B_3601864449 |
|
parameters: |
|
density: 0.9653265129666598 |
|
weight: 0.3766720607532875 |
|
- sources: |
|
- layer_range: [12, 16] |
|
model: ./evol_merge_storage_biomistral_e57b_tydien/input_models/e5-mistral-7b-instruct_2385958088 |
|
parameters: |
|
density: 1.0 |
|
weight: 0.07115038977000693 |
|
- layer_range: [12, 16] |
|
model: ./evol_merge_storage_biomistral_e57b_tydien/input_models/BioMistral-7B_3601864449 |
|
parameters: |
|
density: 1.0 |
|
weight: 0.5584722470438896 |
|
- sources: |
|
- layer_range: [16, 20] |
|
model: ./evol_merge_storage_biomistral_e57b_tydien/input_models/e5-mistral-7b-instruct_2385958088 |
|
parameters: |
|
density: 0.8512047827855883 |
|
weight: 0.452376407390558 |
|
- layer_range: [16, 20] |
|
model: ./evol_merge_storage_biomistral_e57b_tydien/input_models/BioMistral-7B_3601864449 |
|
parameters: |
|
density: 0.8031611968588412 |
|
weight: 0.7515473420070091 |
|
- sources: |
|
- layer_range: [20, 24] |
|
model: ./evol_merge_storage_biomistral_e57b_tydien/input_models/e5-mistral-7b-instruct_2385958088 |
|
parameters: |
|
density: 0.976603252481838 |
|
weight: 0.3562637891615101 |
|
- layer_range: [20, 24] |
|
model: ./evol_merge_storage_biomistral_e57b_tydien/input_models/BioMistral-7B_3601864449 |
|
parameters: |
|
density: 0.6844571720911157 |
|
weight: 0.2577079998117604 |
|
- sources: |
|
- layer_range: [24, 28] |
|
model: ./evol_merge_storage_biomistral_e57b_tydien/input_models/e5-mistral-7b-instruct_2385958088 |
|
parameters: |
|
density: 0.5572225974858718 |
|
weight: 0.6323397851669135 |
|
- layer_range: [24, 28] |
|
model: ./evol_merge_storage_biomistral_e57b_tydien/input_models/BioMistral-7B_3601864449 |
|
parameters: |
|
density: 0.7949919158615303 |
|
weight: 0.7932895770478385 |
|
- sources: |
|
- layer_range: [28, 32] |
|
model: ./evol_merge_storage_biomistral_e57b_tydien/input_models/e5-mistral-7b-instruct_2385958088 |
|
parameters: |
|
density: 1.0 |
|
weight: 0.6731678672160955 |
|
- layer_range: [28, 32] |
|
model: ./evol_merge_storage_biomistral_e57b_tydien/input_models/BioMistral-7B_3601864449 |
|
parameters: |
|
density: 1.0 |
|
weight: 0.24914084912052575 |
|
``` |
|
|