Tarek07's picture
Add files using upload-large-folder tool
f94173c verified
---
base_model:
- flammenai/Mahou-1.5-llama3.1-70B
- nbeerbower/llama3.1-kartoffeldes-70B
- SentientAGI/Dobby-Unhinged-Llama-3.3-70B
- TareksLab/L33R1-T-BASE-70B
- flammenai/Llama3.1-Flammades-70B
- tenyx/Llama3-TenyxChat-70B
library_name: transformers
tags:
- mergekit
- merge
---
# MERGEDL
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 [Linear DELLA](https://arxiv.org/abs/2406.11617) merge method using [TareksLab/L33R1-T-BASE-70B](https://huggingface.co/TareksLab/L33R1-T-BASE-70B) as a base.
### Models Merged
The following models were included in the merge:
* [flammenai/Mahou-1.5-llama3.1-70B](https://huggingface.co/flammenai/Mahou-1.5-llama3.1-70B)
* [nbeerbower/llama3.1-kartoffeldes-70B](https://huggingface.co/nbeerbower/llama3.1-kartoffeldes-70B)
* [SentientAGI/Dobby-Unhinged-Llama-3.3-70B](https://huggingface.co/SentientAGI/Dobby-Unhinged-Llama-3.3-70B)
* [flammenai/Llama3.1-Flammades-70B](https://huggingface.co/flammenai/Llama3.1-Flammades-70B)
* [tenyx/Llama3-TenyxChat-70B](https://huggingface.co/tenyx/Llama3-TenyxChat-70B)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: nbeerbower/llama3.1-kartoffeldes-70B
parameters:
weight: 0.18
density: 0.7
epsilon: 0.2
lambda: 1.1
- model: flammenai/Mahou-1.5-llama3.1-70B
parameters:
weight: 0.16
density: 0.7
epsilon: 0.2
lambda: 1.1
- model: flammenai/Llama3.1-Flammades-70B
parameters:
weight: 0.16
density: 0.7
epsilon: 0.2
lambda: 1.1
- model: SentientAGI/Dobby-Unhinged-Llama-3.3-70B
parameters:
weight: 0.16
density: 0.7
epsilon: 0.2
lambda: 1.1
- model: tenyx/Llama3-TenyxChat-70B
parameters:
weight: 0.16
density: 0.7
epsilon: 0.2
lambda: 1.1
- model: TareksLab/L33R1-T-BASE-70B
parameters:
weight: 0.18
density: 0.7
epsilon: 0.1
lambda: 1.0
merge_method: della_linear
base_model: TareksLab/L33R1-T-BASE-70B
parameters:
normalize: false
int8_mask: true
dtype: float32
out_dtype: bfloat16
chat_template: llama3
tokenizer:
source: union
pad_to_multiple_of: 8
```