---
license: llama2
language:
- it
tags:
- text-generation-inference
---
# Model Card for LLaMAntino-2-7b-evalita

## Model description

<!-- Provide a quick summary of what the model is/does. -->

**LLaMAntino-2-7b-evalita** is a *Large Language Model (LLM)* that is an instruction-tuned version of **LLaMAntino-2-7b** (an italian-adapted **LLaMA 2**). 
This model aims to provide Italian NLP researchers with a tool to tackle tasks such as *sentiment analysis* and *text categorization*.

The model was trained following the methodology used for [Alpaca](https://github.com/tatsu-lab/stanford_alpaca) and using as training data [EVALITA 2023 tasks](https://www.evalita.it/campaigns/evalita-2023/tasks/) formatted in an instruction-following style. 
If you are interested in more details regarding the training procedure, you can find the code we used at the following link:
- **Repository:** https://github.com/swapUniba/LLaMAntino

**NOTICE**: the code has not been released yet, we apologize for the delay, it will be available asap!

- **Developed by:** Pierpaolo Basile, Elio Musacchio, Marco Polignano, Lucia Siciliani, Giuseppe Fiameni, Giovanni Semeraro
- **Funded by:** PNRR project FAIR - Future AI Research
- **Compute infrastructure:** [Leonardo](https://www.hpc.cineca.it/systems/hardware/leonardo/) supercomputer
- **Model type:** Large Language Model (LLM)
- **Language(s) (NLP):** Italian
- **License:** Llama 2 Community License 
- **Finetuned from model:** [swap-uniba/LLaMAntino-2-7b-hf-ITA](https://huggingface.co/swap-uniba/LLaMAntino-2-7b-hf-ITA)

## Prompt Format

This prompt format based on the Alpaca model was used for fine-tuning:

```python
"Di seguito è riportata un'istruzione che descrive un'attività, abbinata ad un input che fornisce ulteriore informazione. " \
"Scrivi una risposta che soddisfi adeguatamente la richiesta.\n\n" \
f"### Istruzione:\n{instruction}\n\n### Input:\n{input}\n\n### Risposta:\n{response}"
```

We recommend using this same prompt in inference to obtain the best results!

## How to Get Started with the Model

Below you can find an example of model usage:

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "swap-uniba/LLaMAntino-2-7b-hf-evalita-ITA"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

instruction_text = "Categorizza le emozioni espresse nel testo fornito in input o determina l'assenza di emozioni. " \
                   "Puoi classificare il testo come neutrale o identificare una o più delle seguenti emozioni: " \
                   "rabbia, anticipazione, disgusto, paura, gioia, tristezza, sorpresa, fiducia, amore."
input_text = "Non me lo aspettavo proprio, ma oggi è stata una bellissima giornata, sono contentissimo!"

prompt = "Di seguito è riportata un'istruzione che descrive un'attività, accompagnata da un input che aggiunge ulteriore informazione. " \
        f"Scrivi una risposta che completi adeguatamente la richiesta.\n\n" \
        f"### Istruzione:\n{instruction_text}\n\n" \
        f"### Input:\n{input_text}\n\n" \
        f"### Risposta:\n"

input_ids = tokenizer(prompt, return_tensors="pt").input_ids
outputs = model.generate(input_ids=input_ids)

print(tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tokens=True)[0][len(prompt):])
```

If you are facing issues when loading the model, you can try to load it quantized:

```python
model = AutoModelForCausalLM.from_pretrained(model_id, token=token, load_in_8bit=True)
```

*Note*: The model loading strategy above requires the [*bitsandbytes*](https://pypi.org/project/bitsandbytes/) and [*accelerate*](https://pypi.org/project/accelerate/) libraries

## Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->

*Coming soon*!

## Citation

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->

If you use this model in your research, please cite the following:

*Coming soon*!