|
--- |
|
base_model: |
|
- mukaj/Llama-3.1-Hawkish-8B |
|
- T145/KRONOS-8B-V1-P3 |
|
- T145/KRONOS-8B-V1-P1 |
|
- unsloth/Meta-Llama-3.1-8B-Instruct |
|
- T145/KRONOS-8B-V1-P2 |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
|
|
--- |
|
# KRONOS 8B V4 |
|
|
|
The goal with this merge is to have a significant step towards why the older TIES merges nuke the IFEval score. Present hypothesis is that merging on the non-instruct model causes this disparity, as IFEval measures instruction-following capacity. It's also possible that either P1 or P3 causes the problem. |
|
|
|
## Merge Details |
|
### Merge Method |
|
|
|
This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [unsloth/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/unsloth/Meta-Llama-3.1-8B-Instruct) as a base. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [mukaj/Llama-3.1-Hawkish-8B](https://huggingface.co/mukaj/Llama-3.1-Hawkish-8B) |
|
* [T145/KRONOS-8B-V1-P3](https://huggingface.co/T145/KRONOS-8B-V1-P3) |
|
* [T145/KRONOS-8B-V1-P1](https://huggingface.co/T145/KRONOS-8B-V1-P1) |
|
* [T145/KRONOS-8B-V1-P2](https://huggingface.co/T145/KRONOS-8B-V1-P2) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
base_model: unsloth/Meta-Llama-3.1-8B-Instruct |
|
dtype: bfloat16 |
|
merge_method: model_stock |
|
slices: |
|
- sources: |
|
- layer_range: [0, 32] |
|
model: T145/KRONOS-8B-V1-P1 |
|
- layer_range: [0, 32] |
|
model: T145/KRONOS-8B-V1-P2 |
|
- layer_range: [0, 32] |
|
model: T145/KRONOS-8B-V1-P3 |
|
- layer_range: [0, 32] |
|
model: mukaj/Llama-3.1-Hawkish-8B |
|
- layer_range: [0, 32] |
|
model: unsloth/Meta-Llama-3.1-8B-Instruct |
|
tokenizer_source: base |
|
``` |
|
|
