---
base_model:
- simonko912/oasst-big-llama
- simonko912/oasst1-llama
- simonko912/oasst2-llama
library_name: transformers
tags:
- mergekit
- merge
- llama
license: apache-2.0
datasets:
- OpenAssistant/oasst1
language:
- en
- es
- ru
---

Simple merges of my diffrent models, then finetuned for 500 steps using lora and oasst1.

Merge kit info below: 

# stacked_model

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:
* [simonko912/oasst-big-llama](https://huggingface.co/simonko912/oasst-big-llama)
* [simonko912/oasst1-llama](https://huggingface.co/simonko912/oasst1-llama)
* [simonko912/oasst2-llama](https://huggingface.co/simonko912/oasst2-llama)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
slices:
  # oasst2-llama repeated 3×
  - sources:
      - model: simonko912/oasst2-llama
        layer_range: [0, 12]
  - sources:
      - model: simonko912/oasst2-llama
        layer_range: [0, 12]
  - sources:
      - model: simonko912/oasst2-llama
        layer_range: [0, 12]

  # oasst-big-llama
  - sources:
      - model: simonko912/oasst-big-llama
        layer_range: [0, 12]

  # oasst1-llama
  - sources:
      - model: simonko912/oasst1-llama
        layer_range: [0, 12]

merge_method: passthrough
dtype: bfloat16

```