55 lines
1.3 KiB
Markdown
55 lines
1.3 KiB
Markdown
---
|
|
base_model:
|
|
- TroyDoesAI/Llama-3.1-8B-Instruct
|
|
library_name: transformers
|
|
tags:
|
|
- mergekit
|
|
- merge
|
|
|
|
---
|
|
# Llama-3.1-13B-Instruct
|
|
|
|
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:
|
|
* [TroyDoesAI/Llama-3.1-8B-Instruct](https://huggingface.co/TroyDoesAI/Llama-3.1-8B-Instruct)
|
|
|
|
### Configuration
|
|
|
|
The following YAML configuration was used to produce this model:
|
|
|
|
```yaml
|
|
#### BEST CONFIGURATION ####
|
|
slices:
|
|
- sources:
|
|
- layer_range: [0, 8]
|
|
model: TroyDoesAI/Llama-3.1-8B-Instruct
|
|
- sources:
|
|
- layer_range: [4, 12]
|
|
model: TroyDoesAI/Llama-3.1-8B-Instruct
|
|
- sources:
|
|
- layer_range: [8, 16]
|
|
model: TroyDoesAI/Llama-3.1-8B-Instruct
|
|
- sources:
|
|
- layer_range: [12, 20]
|
|
model: TroyDoesAI/Llama-3.1-8B-Instruct
|
|
- sources:
|
|
- layer_range: [16, 24]
|
|
model: TroyDoesAI/Llama-3.1-8B-Instruct
|
|
- sources:
|
|
- layer_range: [20, 28]
|
|
model: TroyDoesAI/Llama-3.1-8B-Instruct
|
|
- sources:
|
|
- layer_range: [24, 32]
|
|
model: TroyDoesAI/Llama-3.1-8B-Instruct
|
|
merge_method: passthrough
|
|
dtype: bfloat16
|
|
```
|