🧠 Llama-3.2-1B-Instruct — IMB Medicina Generale Fine-Tuned Model
This model is a fine-tuned version of
unsloth/Llama-3.2-1B-Instruct-unsloth-bnb-4bit, optimized for
Italian medical question answering, with a specific focus on
Medicina Generale.
The fine-tuning was performed using a subset of the IMB (Italian Medical Benchmark) dataset, specifically:
- Medicina Generale category only
- ~10,000 training samples
The training was performed using the Unsloth library with LoRA fine-tuning, and the adapter weights were later merged into the base model to provide a standalone checkpoint.
This model relies on data from the IMB dataset. If you use this model in research or applications, you must cite the IMB paper (see Citation section below).
📚 Training Dataset — IMB (Italian Medical Benchmark)
IMB is an Italian benchmark for medical question answering, designed to evaluate and improve LLM performance in clinical-domain Italian language understanding and reasoning.
The full dataset includes:
- IMB-QA: 782,644 doctor-patient conversations collected from Italian online medical forums
- IMB-MCQA: 25,862 multiple-choice questions derived from Italian medical specialization exams
⚠️ Important:
This model was trained only on the Medicina Generale subset (~10,000 samples) of IMB, not on the full dataset.
🧪 Usage Example
1from transformers import AutoModelForCausalLM, AutoTokenizer
2
3model = AutoModelForCausalLM.from_pretrained("praiselab-picuslab/Llama-3.2-1B-Instruct-Medicina Generale")
4tokenizer = AutoTokenizer.from_pretrained("praiselab-picuslab/Llama-3.2-1B-Instruct-Medicina Generale")
5
6prompt = "[Example question in Italian about Medicina Generale]"
7inputs = tokenizer(prompt, return_tensors="pt")
8outputs = model.generate(**inputs, max_new_tokens=150)
9
10print(tokenizer.decode(outputs[0], skip_special_tokens=True))
⚠️ Usage Restrictions
- Allowed use: Non-commercial research only
- Redistribution: Not allowed without explicit authorization
- Mandatory citation: The IMB dataset paper must be cited in any publication or derived work
📄 Citation
If you use this model, the IMB dataset, or derived outputs in research, please cite:
1@inproceedings{DBLP:conf/clic-it/RomanoRBPM25,
2 author = {Antonio Romano and
3 Giuseppe Riccio and
4 Mariano Barone and
5 Marco Postiglione and
6 Vincenzo Moscato},
7 editor = {Cristina Bosco and
8 Elisabetta Jezek and
9 Marco Polignano and
10 Manuela Sanguinetti},
11 title = {{IMB:} An Italian Medical Benchmark for Question Answering},
12 booktitle = {Proceedings of the Eleventh Italian Conference on Computational Linguistics
13 (CLiC-it 2025), Cagliari, Italy, September 24-26, 2025},
14 series = {{CEUR} Workshop Proceedings},
15 volume = {4112},
16 publisher = {CEUR-WS.org},
17 year = {2025},
18 url = {https://ceur-ws.org/Vol-4112/92_main_long.pdf}
19}
🏗 Training Details
- Base model:
unsloth/Llama-3.2-1B-Instruct-unsloth-bnb-4bit
- Fine-tuning method: LoRA (Unsloth)
- Quantization: 4-bit (BitsAndBytes)
- Adapter merging: Yes (Full merged model)
- Language: Italian
- Domain: Medical — Medicina Generale
- Training size: ~10,000 samples
📜 License
🤝 Acknowledgements
👨💻 This project was developed by Mariano Barone, Roberta Di Marino, Francesco Di Serio, Giovanni Dioguardi, Marco Postiglione, Antonio Romano, Giuseppe Riccio, and Vincenzo Moscato at University of Naples, Federico II
