---
base_model:
- schonsense/70B_Chunky_stock
- meta-llama/Llama-3.3-70B-Instruct
- schonsense/VAR_stock
library_name: transformers
tags:
- mergekit
- merge

---
# FT_BC

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:
* [schonsense/70B_Chunky_stock](https://huggingface.co/schonsense/70B_Chunky_stock)
* D:\mergekit\LORAs\applied\70B_ERA2_sun_r256
* D:\mergekit\_My_YAMLS\ERA2_stock
* [schonsense/VAR_stock](https://huggingface.co/schonsense/VAR_stock)
* D:\mergekit\_My_YAMLS\Book_stock

### Configuration

The following YAML configuration was used to produce this model:

```yaml
merge_method: breadcrumbs

models:
   
  - model: "D:\\mergekit\\_My_YAMLS\\ERA2_stock"
    parameters:
      gamma: 0.01
      density: .4
      weight: 0.2  

  - model: "D:\\mergekit\\_My_YAMLS\\Book_stock"
    parameters:
      gamma: 0.0
      density: .6
      weight: 0.3  

  - model: schonsense/70B_Chunky_stock
    parameters:
      gamma: 0.01
      density: .3
      weight: 0.2  

  - model: "D:\\mergekit\\LORAs\\applied\\70B_ERA2_sun_r256"
    parameters:
      gamma: 0.02
      density: .3
      weight: 0.2  

  - model: schonsense/VAR_stock
    parameters:
      gamma: 0.02
      density: .5
      weight: 0.1  
 
  - model: meta-llama/Llama-3.3-70B-Instruct

base_model: meta-llama/Llama-3.3-70B-Instruct

parameters:
  normalize: true
  int8_mask: true
  lambda: 1

dtype: float32
out_dtype: bfloat16

tokenizer:
  source: union
  pad_to_multiple_of: 8
```