README.md

---
base_model:
- swap-uniba/LLaMAntino-3-ANITA-8B-Inst-DPO-ITA
- DeepMount00/Llama-3-8b-Ita
library_name: transformers
tags:
- mergekit
- merge
license: llama3
language:
- it
---
# Llama-3-8b-ita-slerp

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

I tried to merge two of the best Italian LLMs using Mergekit. The results are acceptable, but I could not improve on the best existing model.

## Evaluation

For a detailed comparison of model performance, check out the [Leaderboard for Italian Language Models](https://huggingface.co/spaces/FinancialSupport/open_ita_llm_leaderboard).

Here's a breakdown of the performance metrics:

| Metric                      | hellaswag_it acc_norm | arc_it acc_norm | m_mmlu_it 5-shot acc | Average |
|:----------------------------|:----------------------|:----------------|:---------------------|:--------|
| **Accuracy Normalized**     | 0.6879               | 0.5714        | 0.5732              | 0.6109  |

## Merge Details
### Merge Method

This model was merged using the SLERP merge method.

### Models Merged

The following models were included in the merge:
* [swap-uniba/LLaMAntino-3-ANITA-8B-Inst-DPO-ITA](https://huggingface.co/swap-uniba/LLaMAntino-3-ANITA-8B-Inst-DPO-ITA)
* [DeepMount00/Llama-3-8b-Ita](https://huggingface.co/DeepMount00/Llama-3-8b-Ita)

### Configuration

The following YAML configuration was used to produce this model:

```yaml

slices:
- sources:
  - model: swap-uniba/LLaMAntino-3-ANITA-8B-Inst-DPO-ITA
    layer_range:
    - 0
    - 32
  - model: DeepMount00/Llama-3-8b-Ita
    layer_range:
    - 0
    - 32
merge_method: slerp
base_model: swap-uniba/LLaMAntino-3-ANITA-8B-Inst-DPO-ITA
parameters:
  t:
  - filter: self_attn
    value:
    - 0
    - 0.5
    - 0.3
    - 0.7
    - 1
  - filter: mlp
    value:
    - 1
    - 0.5
    - 0.7
    - 0.3
    - 0
  - value: 0.5
dtype: bfloat16

```