---
base_model:
- Salesforce/SFR-Iterative-DPO-LLaMA-3-8B-R
library_name: transformers
tags:
- mergekit
- merge

---
A zero training self-merge test of [Salesforce/SFR-Iterative-DPO-LLaMA-3-8B-R](https://huggingface.co/Salesforce/SFR-Iterative-DPO-LLaMA-3-8B-R) using settings mentioned on [mistral-11b-slimorca](https://huggingface.co/chargoddard/mistral-11b-slimorca)<br>
It's....not dumber I guess 🤷‍♀️

Simple PPL comparison<br>
<code>
<i>perplexity.exe -[MODEL] -f wiki.test.raw -b 512 -ngl 99</i><br>
<i>SFR-Iterative-DPO-LLaMA-3-8B-R-F16.gguf</i> - Final estimate: <b>PPL = 7.0279 +/- 0.04493</b><br>
<i>SFR-Iterative-DPO-LLaMA-3-11.5B-R-Q6_K.gguf</i> - Final estimate: <b>PPL = 7.0500 +/- 0.04516</b><br>
<i>Meta-Llama-3-8B-Instruct-Q6_K</i> - Final estimate: <b>PPL = 8.4727 +/- 0.06308</b>
</code>

<b><u>Tools used / version</u></b><br>
<b>Mergekit:</b> <i>c93c9bb</i><br>
<b>llama.cpp:</b> <i>b2876</i>


# merged

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 passthrough merge method.

### Models Merged

The following models were included in the merge:
* [Salesforce/SFR-Iterative-DPO-LLaMA-3-8B-R](https://huggingface.co/Salesforce/SFR-Iterative-DPO-LLaMA-3-8B-R)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 24]
    model: Salesforce/SFR-Iterative-DPO-LLaMA-3-8B-R
- sources:
  - layer_range: [8, 24]
    model: Salesforce/SFR-Iterative-DPO-LLaMA-3-8B-R
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [24, 32]
    model: Salesforce/SFR-Iterative-DPO-LLaMA-3-8B-R
```