|
|
--- |
|
|
base_model: |
|
|
- NeverSleep/Lumimaid-v0.2-70B |
|
|
- Undi95/Sushi-v1.4 |
|
|
- ArliAI/Llama-3.3-70B-ArliAI-RPMax-v1.4 |
|
|
- Sao10K/L3.1-70B-Hanami-x1 |
|
|
- SicariusSicariiStuff/Negative_LLAMA_70B |
|
|
- meta-llama/Llama-3.3-70B-Instruct |
|
|
library_name: transformers |
|
|
tags: |
|
|
- mergekit |
|
|
- merge |
|
|
license: llama3.3 |
|
|
--- |
|
|
# merge |
|
|
|
|
|
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 [Model Breadcrumbs](https://arxiv.org/abs/2312.06795) merge method using [meta-llama/Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct) as a base. |
|
|
|
|
|
### Models Merged |
|
|
|
|
|
The following models were included in the merge: |
|
|
* [NeverSleep/Lumimaid-v0.2-70B](https://huggingface.co/NeverSleep/Lumimaid-v0.2-70B) |
|
|
* [Undi95/Sushi-v1.4](https://huggingface.co/Undi95/Sushi-v1.4) |
|
|
* [ArliAI/Llama-3.3-70B-ArliAI-RPMax-v1.4](https://huggingface.co/ArliAI/Llama-3.3-70B-ArliAI-RPMax-v1.4) |
|
|
* [Sao10K/L3.1-70B-Hanami-x1](https://huggingface.co/Sao10K/L3.1-70B-Hanami-x1) |
|
|
* [SicariusSicariiStuff/Negative_LLAMA_70B](https://huggingface.co/SicariusSicariiStuff/Negative_LLAMA_70B) |
|
|
|
|
|
### Configuration |
|
|
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
|
|
```yaml |
|
|
models: |
|
|
- model: Undi95/Sushi-v1.4 |
|
|
parameters: |
|
|
weight: 0.20 |
|
|
density: 0.9 |
|
|
- model: NeverSleep/Lumimaid-v0.2-70B |
|
|
parameters: |
|
|
weight: 0.20 |
|
|
density: 0.9 |
|
|
- model: ArliAI/Llama-3.3-70B-ArliAI-RPMax-v1.4 |
|
|
parameters: |
|
|
weight: 0.20 |
|
|
density: 0.9 |
|
|
- model: Sao10K/L3.1-70B-Hanami-x1 |
|
|
parameters: |
|
|
weight: 0.20 |
|
|
density: 0.9 |
|
|
- model: SicariusSicariiStuff/Negative_LLAMA_70B |
|
|
parameters: |
|
|
weight: 0.20 |
|
|
density: 0.9 |
|
|
merge_method: breadcrumbs |
|
|
base_model: meta-llama/Llama-3.3-70B-Instruct |
|
|
parameters: |
|
|
gamma: 0.01 |
|
|
lambda: 1.1 |
|
|
normalize: false |
|
|
int8_mask: true |
|
|
out_dtype: bfloat16 |
|
|
tokenizer: |
|
|
source: SicariusSicariiStuff/Negative_LLAMA_70B |
|
|
``` |
|
|
|
