Llamantino 2 7b Hf ITA

🚀 LLaMAntino-2-7b-ITA

LLaMAntino-2-7b-ITA is an Italian-adapted Large Language Model (LLM) based on LLaMA 2, aiming to offer a base model for Italian NLP researchers in natural language generation tasks.

🚀 Quick Start

Below is an example of how to use the LLaMAntino-2-7b-ITA model:

Basic Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

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

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

prompt = "Scrivi qui un possibile prompt"

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

print(tokenizer.batch_decode(outputs.detach().cpu().numpy()[:, input_ids.shape[1]:], skip_special_tokens=True)[0])

Advanced Usage

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

model = AutoModelForCausalLM.from_pretrained(model_id, load_in_8bit=True)

⚠️ Important Note

The model loading strategy above requires the bitsandbytes and accelerate libraries

✨ Features

LLaMAntino-2-7b is an Italian-adapted LLaMA 2 Large Language Model (LLM). It is designed to provide Italian NLP researchers with a base model for natural language generation tasks.

📦 Installation

The installation process mainly involves installing the necessary Python libraries. You can use pip to install them:

pip install transformers bitsandbytes accelerate

📚 Documentation

Model Information

Training Details

The model was trained using QLora and the training data is clean_mc4_it medium. If you are interested in more details regarding the training procedure, you can find the code at the following link:

• Repository: https://github.com/swapUniba/LLaMAntino

⚠️ Important Note

The code has not been released yet. We apologize for the delay, and it will be available asap!

📄 License

Llama 2 is licensed under the LLAMA 2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved. License

📚 Citation

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

@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}
}