|
--- |
|
base_model: |
|
- Replete-AI/Replete-Coder-Llama3-8B |
|
- Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
license: llama3 |
|
language: |
|
- en |
|
--- |
|
# Llama-3-Umbral-Mind-Replete-8B |
|
|
|
Copied the merge script from [tannedbum/L3-Nymeria-8B](https://huggingface.co/tannedbum/L3-Nymeria-8B) and made it use [Replete-AI/Replete-Coder-Llama3-8B](https://huggingface.co/Replete-AI/Replete-Coder-Llama3-8B) with [Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B](https://huggingface.co/Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B) as the base model instead. |
|
|
|
It appears to talk a lot for some reason, regardless what is instructed. |
|
|
|
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 SLERP merge method. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [Replete-AI/Replete-Coder-Llama3-8B](https://huggingface.co/Replete-AI/Replete-Coder-Llama3-8B) |
|
* [Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B](https://huggingface.co/Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
|
|
slices: |
|
- sources: |
|
- model: Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B |
|
layer_range: [0, 32] |
|
- model: Replete-AI/Replete-Coder-Llama3-8B |
|
layer_range: [0, 32] |
|
merge_method: slerp |
|
base_model: Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B |
|
parameters: |
|
t: |
|
- filter: self_attn |
|
value: [0.4, 0.5, 0.6, 0.4, 0.6] |
|
- filter: mlp |
|
value: [0.6, 0.5, 0.4, 0.6, 0.4] |
|
- value: 0.5 |
|
dtype: bfloat16 |
|
|
|
``` |
