---
base_model:
- Steelskull/L3.3-MS-Nevoria-70b
- Nohobby/L3.3-Prikol-70B-v0.3
- Tarek07/Progenitor-V1.1-LLaMa-70B
- sophosympatheia/Nova-Tempus-70B-v0.1
- nbeerbower/Llama-3.1-Nemotron-lorablated-70B
- Tarek07/Progenitor-V1.2-LLaMa-70B
library_name: transformers
tags:
- mergekit
- merge
license: llama3.3
---
This one didn't come out right, I feel it's inferior to it's predecessor. But that is only from early testing.
# 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 [Linear DELLA](https://arxiv.org/abs/2406.11617) merge method using [nbeerbower/Llama-3.1-Nemotron-lorablated-70B](https://huggingface.co/nbeerbower/Llama-3.1-Nemotron-lorablated-70B) as a base.

### Models Merged

The following models were included in the merge:
* [Steelskull/L3.3-MS-Nevoria-70b](https://huggingface.co/Steelskull/L3.3-MS-Nevoria-70b)
* [Nohobby/L3.3-Prikol-70B-v0.3](https://huggingface.co/Nohobby/L3.3-Prikol-70B-v0.3)
* [Tarek07/Progenitor-V1.1-LLaMa-70B](https://huggingface.co/Tarek07/Progenitor-V1.1-LLaMa-70B)
* [sophosympatheia/Nova-Tempus-70B-v0.1](https://huggingface.co/sophosympatheia/Nova-Tempus-70B-v0.1)
* [Tarek07/Progenitor-V1.2-LLaMa-70B](https://huggingface.co/Tarek07/Progenitor-V1.2-LLaMa-70B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: Steelskull/L3.3-MS-Nevoria-70b
    parameters:
      weight: 0.20
      density: 0.7
  - model: Nohobby/L3.3-Prikol-70B-v0.3
    parameters:
      weight: 0.20
      density: 0.7
  - model: Tarek07/Progenitor-V1.2-LLaMa-70B
    parameters:
      weight: 0.20
      density: 0.7
  - model: Tarek07/Progenitor-V1.1-LLaMa-70B
    parameters:
      weight: 0.20
      density: 0.7
  - model: sophosympatheia/Nova-Tempus-70B-v0.1
    parameters:
      weight: 0.20
      density: 0.7
merge_method: della_linear
base_model: nbeerbower/Llama-3.1-Nemotron-lorablated-70B
parameters:
  epsilon: 0.2
  lambda: 1.1
dtype: bfloat16
tokenizer_source: base

```