---
base_model: []
library_name: transformers
tags:
- mergekit
- merge
license: llama3.3
---
I was curious about using Euryale as the base for Progenitor for a while, this is the result.
# Progenitor-V3.2-70B

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 D:/mergekit_models/L3.3-70B-Euryale-v2.3 as a base.

### Models Merged

The following models were included in the merge:
* D:/mergekit_models/Negative_LLAMA_70B
* D:/mergekit_models/L3.1-70B-Hanami-x1
* D:/mergekit_models/EVA-LLaMA-3.33-70B-v0.1
* D:/mergekit_models//70B-L3.3-Cirrus-x1
* D:/mergekit_models/Anubis-70B-v1

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: D:/mergekit_models/L3.1-70B-Hanami-x1
    parameters:
      weight: 0.20
      density: 0.7
  - model: D:/mergekit_models//70B-L3.3-Cirrus-x1
    parameters:
      weight: 0.20
      density: 0.7
  - model: D:/mergekit_models/Negative_LLAMA_70B
    parameters:
      weight: 0.20
      density: 0.7
  - model: D:/mergekit_models/Anubis-70B-v1
    parameters:
      weight: 0.20
      density: 0.7
  - model: D:/mergekit_models/EVA-LLaMA-3.33-70B-v0.1
    parameters:
      weight: 0.20
      density: 0.7
merge_method: della_linear
base_model: D:/mergekit_models/L3.3-70B-Euryale-v2.3
parameters:
  epsilon: 0.2
  lambda: 1.1
dype: float32
out_dtype: bfloat16
tokenizer:
 source: base
```