---
base_model:
- unsloth/Meta-Llama-3.1-8B
- unsloth/Meta-Llama-3.1-8B-Instruct
library_name: transformers
tags:
- mergekit
- merge

---
# merge

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](https://arxiv.org/abs/2203.05482) merge method.

### Models Merged

The following models were included in the merge:
* [unsloth/Meta-Llama-3.1-8B](https://huggingface.co/unsloth/Meta-Llama-3.1-8B)
* [unsloth/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/unsloth/Meta-Llama-3.1-8B-Instruct)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
merge_method: linear
dtype: float32
out_dtype: bfloat16
models:
  - model: unsloth/Meta-Llama-3.1-8B
    parameters:
      weight: 1.0
  - model: unsloth/Meta-Llama-3.1-8B-Instruct
    parameters:
      weight: 0.0
tokenizer:
  source: unsloth/Meta-Llama-3.1-8B-Instruct
  tokens:
    <|begin_of_text|>:
      source: unsloth/Meta-Llama-3.1-8B-Instruct
      force: true
    <|end_of_text|>:
      source: unsloth/Meta-Llama-3.1-8B-Instruct
      force: true
    <|finetune_right_pad_id|>:
      source: unsloth/Meta-Llama-3.1-8B-Instruct
      force: true
    <|start_header_id|>:
      source: unsloth/Meta-Llama-3.1-8B-Instruct
      force: true
    <|end_header_id|>:
      source: unsloth/Meta-Llama-3.1-8B-Instruct
      force: true
    <|eom_id|>:
      source: unsloth/Meta-Llama-3.1-8B-Instruct
      force: true
    <|eot_id|>:
      source: unsloth/Meta-Llama-3.1-8B-Instruct
      force: true
    <|python_tag|>:
      source: unsloth/Meta-Llama-3.1-8B-Instruct
      force: true
    <|eot_id|>:
      source: unsloth/Meta-Llama-3.1-8B-Instruct
      force: true
    <|eot_id|>:
      source: unsloth/Meta-Llama-3.1-8B-Instruct
      force: true
```