Instructions to use SemanticAlignment/Mistral-v0.1-Italian-LAPT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SemanticAlignment/Mistral-v0.1-Italian-LAPT with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="SemanticAlignment/Mistral-v0.1-Italian-LAPT")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SemanticAlignment/Mistral-v0.1-Italian-LAPT")
model = AutoModelForCausalLM.from_pretrained("SemanticAlignment/Mistral-v0.1-Italian-LAPT", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SemanticAlignment/Mistral-v0.1-Italian-LAPT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SemanticAlignment/Mistral-v0.1-Italian-LAPT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SemanticAlignment/Mistral-v0.1-Italian-LAPT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/SemanticAlignment/Mistral-v0.1-Italian-LAPT

SGLang

How to use SemanticAlignment/Mistral-v0.1-Italian-LAPT with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "SemanticAlignment/Mistral-v0.1-Italian-LAPT" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SemanticAlignment/Mistral-v0.1-Italian-LAPT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "SemanticAlignment/Mistral-v0.1-Italian-LAPT" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SemanticAlignment/Mistral-v0.1-Italian-LAPT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use SemanticAlignment/Mistral-v0.1-Italian-LAPT with Docker Model Runner:
```
docker model run hf.co/SemanticAlignment/Mistral-v0.1-Italian-LAPT
```

Mistral-v0.1-Italian-LAPT / README.md

nielsr HF Staff

Add pipeline tag and library name

4317485 verified over 1 year ago

preview code

Raw History Blame

2.38 kB

---
language:
- it
- en
license: apache-2.0
pipeline_tag: text-generation
library_name: transformers
---
# Mistral-7B-v0.1-Italian-LAPT
<div align="center">

<img src="https://github.com/Andrew-Wyn/images/blob/master/sava/italian_adapt-img.jpg?raw=true" width="400" height="400" style="border-radius:10%" />

</div>

The **Mistral-7B-v0.1-Adapted** collection of large language models (LLMs), is a collection of adapted generative models in 7B (text in/text out), adapted models from **Mistral-7B-Base-v0.1**.

*Mistral-v0.1-Italian-LAPT* is a continual trained mistral model.

**Model developer:** SapienzaNLP, ISTI-CNR, ILC-CNR

**Model Architecture:** Mistral-7B-v0.1-Adapted is an auto-regressive language model that uses an optimized transformer architecture.

## Data used for the adaptation

The **Mistral-7B-v0.1-Adapted** model are trained on a collection of Italian and English data extracted from [CulturaX](https://huggingface.co/datasets/uonlp/CulturaX).
The data are extracted to be skewed toward Italian language with a ration of one over four. Extracting the first 9B tokens from Italian part of CulturaX and the first 3B tokens from English part of CulturaX.


## Use with Transformers

You can run conversational inference using the Transformers pipeline abstraction or by leveraging the Auto classes with the generate() function.

Make sure to update your transformers installation via pip install --upgrade transformers.

```python
import transformers
import torch
model_id = "SemanticAlignment/Mistral-v0.1-Italian-LAPT"
pipeline = transformers.pipeline(
    "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device_map="auto"
)
pipeline("Cosa si può fare in una bella giornata di sole?")
```

## Citation

If you use any part of this work, please consider citing the paper as follows:

```bibtex
@misc{moroni2025optimizingllmsitalianreducing,
      title={Optimizing LLMs for Italian: Reducing Token Fertility and Enhancing Efficiency Through Vocabulary Adaptation}, 
      author={Luca Moroni and Giovanni Puccetti and Pere-Lluis Huguet Cabot and Andrei Stefan Bejgu and Edoardo Barba and Alessio Miaschi and Felice Dell'Orletta and Andrea Esuli and Roberto Navigli},
      year={2025},
      eprint={2504.17025},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2504.17025}, 
}
```

	---
	language:
	- it
	- en
	license: apache-2.0
	pipeline_tag: text-generation
	library_name: transformers
	---

	# Mistral-7B-v0.1-Italian-LAPT
	<div align="center">

	<img src="https://github.com/Andrew-Wyn/images/blob/master/sava/italian_adapt-img.jpg?raw=true" width="400" height="400" style="border-radius:10%" />

	</div>

	The Mistral-7B-v0.1-Adapted collection of large language models (LLMs), is a collection of adapted generative models in 7B (text in/text out), adapted models from Mistral-7B-Base-v0.1.

	Mistral-v0.1-Italian-LAPT is a continual trained mistral model.

	Model developer: SapienzaNLP, ISTI-CNR, ILC-CNR

	Model Architecture: Mistral-7B-v0.1-Adapted is an auto-regressive language model that uses an optimized transformer architecture.

	## Data used for the adaptation

	The Mistral-7B-v0.1-Adapted model are trained on a collection of Italian and English data extracted from [CulturaX](https://huggingface.co/datasets/uonlp/CulturaX).
	The data are extracted to be skewed toward Italian language with a ration of one over four. Extracting the first 9B tokens from Italian part of CulturaX and the first 3B tokens from English part of CulturaX.


	## Use with Transformers

	You can run conversational inference using the Transformers pipeline abstraction or by leveraging the Auto classes with the generate() function.

	Make sure to update your transformers installation via pip install --upgrade transformers.

	```python
	import transformers
	import torch

	model_id = "SemanticAlignment/Mistral-v0.1-Italian-LAPT"

	pipeline = transformers.pipeline(
	"text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device_map="auto"
	)

	pipeline("Cosa si può fare in una bella giornata di sole?")
	```

	## Citation

	If you use any part of this work, please consider citing the paper as follows:

	```bibtex
	@misc{moroni2025optimizingllmsitalianreducing,
	title={Optimizing LLMs for Italian: Reducing Token Fertility and Enhancing Efficiency Through Vocabulary Adaptation},
	author={Luca Moroni and Giovanni Puccetti and Pere-Lluis Huguet Cabot and Andrei Stefan Bejgu and Edoardo Barba and Alessio Miaschi and Felice Dell'Orletta and Andrea Esuli and Roberto Navigli},
	year={2025},
	eprint={2504.17025},
	archivePrefix={arXiv},
	primaryClass={cs.CL},
	url={https://arxiv.org/abs/2504.17025},
	}
	```