README.md

---
datasets:
- gsarti/clean_mc4_it
- Chat-Error/wizard_alpaca_dolly_orca
- mlabonne/orpo-dpo-mix-40k
base_model: meta-llama/Meta-Llama-3-8B-Instruct
model_creator: Marco Polignano - SWAP Research Group
language:
- en
- it
metrics:
- accuracy
pipeline_tag: text-generation
tags:
- facebook
- meta
- pythorch
- llama
- llama-3
- llamantino
library_name: transformers
license: llama3
---
<img src="https://cdn-uploads.huggingface.co/production/uploads/5df8bb21da6d0311fd3d540f/xL6Ax1I34qfC4VPKEFA6Z.png" alt="llamantino3_anita" border="0" width="800px">
<hr>
<!--<img src="https://i.ibb.co/6mHSRm3/llamantino53.jpg" width="200"/>-->
<h3><i>"Built with <b>Meta Llama 3</b>".</i></i></h3>
<p style="text-align:justify;"><b>LLaMAntino-3-ANITA-8B-Inst-DPO-ITA</b> is a model of the <a href="https://huggingface.co/swap-uniba"><b>LLaMAntino</b></a> - <i>Large Language Models family</i>.
The model is an instruction-tuned version of <a href="https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct"><b>Meta-Llama-3-8b-instruct</b></a> (a fine-tuned <b>LLaMA 3 model</b>).
This model version aims to be the a <b>Multilingual Model</b> 🏁  (EN 🇺🇸 + ITA🇮🇹) to further fine-tuning on Specific Tasks in Italian.</p>


The 🌟**ANITA project**🌟 *(**A**dvanced **N**atural-based interaction for the **ITA**lian language)*
wants to provide Italian NLP researchers with an improved model for the Italian Language 🇮🇹 use cases.

<hr>

## Model Details

<img src="https://static.vecteezy.com/system/resources/previews/016/833/880/large_2x/github-logo-git-hub-icon-with-text-on-white-background-free-vector.jpg" width="200"> [https://github.com/marcopoli/LLaMAntino-3-ANITA](https://github.com/marcopoli/LLaMAntino-3-ANITA)<br>

<br>

- [**Full Model: LaMAntino-3-ANITA-8B-Inst-DPO-ITA**](https://huggingface.co/swap-uniba/LLaMAntino-3-ANITA-8B-Inst-DPO-ITA)
- LLaMA.cpp - **F16 model**
- LLaMA.cpp - **Q8_0 model** 
- LLaMA.cpp - **Q4_K_M model** 
- LLaMA.cpp - **Q2_K model** 

<hr>

## Specifications

- **Model developers**: <br><a href="https://marcopoli.github.io/">Ph.D. Marco Polignano</a> - University of Bari Aldo Moro, Italy <br> <a href="https://huggingface.co/swap-uniba">SWAP Research Group</a> <br>
- **Variations**: The model release has been **supervised fine-tuning (SFT)** using **QLoRA** 4bit, on instruction-based datasets. **DPO** approach over the *mlabonne/orpo-dpo-mix-40k* dataset is used to align with human preferences for helpfulness and safety.
- **Input**: Models input text only.
- **Language**: Multilingual 🏁 + Italian 🇮🇹
- **Output**: Models generate text and code only.
- **Model Architecture**: *Llama 3 architecture*.
- **Context length**: 8K, 8192.
- **Library Used**: [LLaMA.cpp](https://github.com/ggerganov/llama.cpp)
  
<hr>

### Prompt Template
```
<|start_header_id|>system<|end_header_id|>

{ SYS Prompt }<|eot_id|><|start_header_id|>user<|end_header_id|>

{ USER Prompt }<|eot_id|><|start_header_id|>assistant<|end_header_id|>

{ ASSIST Prompt }<|eot_id|>
````

<hr>

## LLaMA.cpp

<img src="https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png" width="200px" align="center" />

[LLaMA.cpp](https://github.com/ggerganov/llama.cpp), a great tool that helps us easily Quantize your model in **GGUF format**.

## Citation instructions
```bibtex
@misc{polignano2024advanced,
      title={Advanced Natural-based interaction for the ITAlian language: LLaMAntino-3-ANITA}, 
      author={Marco Polignano and Pierpaolo Basile and Giovanni Semeraro},
      year={2024},
      eprint={2405.07101},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}
```

```bibtex
@misc{basile2023llamantino,
      title={LLaMAntino: LLaMA 2 Models for Effective Text Generation in Italian Language}, 
      author={Pierpaolo Basile and Elio Musacchio and Marco Polignano and Lucia Siciliani and Giuseppe Fiameni and Giovanni Semeraro},
      year={2023},
      eprint={2312.09993},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}
```

```bibtex
@article{llama3modelcard,
  title={Llama 3 Model Card},
  author={AI@Meta},
  year={2024},
  url = {https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md}
}
```