---
base_model: []
library_name: transformers
tags:
- mergekit
- merge

---
# prototype-0.4x104

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 [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using /workspace/prototype-0.4x102 as a base.

### Models Merged

The following models were included in the merge:
* /workspace/cache/models--Envoid--Llama-3-TenyxChat-DaybreakStorywriter-70B/snapshots/2416e680265cfe7818defa218fb8e9fdac04a8c1
* /workspace/cache/models--Envoid--L3-TenyxChat-Daybreak-Storywriter-RAE-70B/snapshots/0b064cc049343d152d45b30069feb2223d77ee9f

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: /workspace/cache/models--Envoid--Llama-3-TenyxChat-DaybreakStorywriter-70B/snapshots/2416e680265cfe7818defa218fb8e9fdac04a8c1
    parameters:
      weight: 0.35
      density: 0.7
  - model: /workspace/cache/models--Envoid--L3-TenyxChat-Daybreak-Storywriter-RAE-70B/snapshots/0b064cc049343d152d45b30069feb2223d77ee9f
    parameters:
      weight: 0.35
      density: 0.7
  - model: /workspace/prototype-0.4x102
    parameters:
      weight: 0.35
      density: 0.7
merge_method: dare_ties
base_model: /workspace/prototype-0.4x102
parameters:
  normalize: true
  lambda: .95
dtype: bfloat16
int8_mask: true
chat_template: llama3
tokenizer:
 source: base
```