Instructions to use sapienzanlp/Minerva-3B-base-v1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sapienzanlp/Minerva-3B-base-v1.0 with Transformers:

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

pipe = pipeline("text-generation", model="sapienzanlp/Minerva-3B-base-v1.0")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sapienzanlp/Minerva-3B-base-v1.0")
model = AutoModelForCausalLM.from_pretrained("sapienzanlp/Minerva-3B-base-v1.0")

llama-cpp-python

How to use sapienzanlp/Minerva-3B-base-v1.0 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="sapienzanlp/Minerva-3B-base-v1.0",
	filename="minerva-3b.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use sapienzanlp/Minerva-3B-base-v1.0 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf sapienzanlp/Minerva-3B-base-v1.0
# Run inference directly in the terminal:
llama-cli -hf sapienzanlp/Minerva-3B-base-v1.0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf sapienzanlp/Minerva-3B-base-v1.0
# Run inference directly in the terminal:
llama-cli -hf sapienzanlp/Minerva-3B-base-v1.0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf sapienzanlp/Minerva-3B-base-v1.0
# Run inference directly in the terminal:
./llama-cli -hf sapienzanlp/Minerva-3B-base-v1.0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf sapienzanlp/Minerva-3B-base-v1.0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf sapienzanlp/Minerva-3B-base-v1.0

Use Docker

docker model run hf.co/sapienzanlp/Minerva-3B-base-v1.0

LM Studio
Jan

vLLM

How to use sapienzanlp/Minerva-3B-base-v1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sapienzanlp/Minerva-3B-base-v1.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sapienzanlp/Minerva-3B-base-v1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/sapienzanlp/Minerva-3B-base-v1.0

SGLang

How to use sapienzanlp/Minerva-3B-base-v1.0 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 "sapienzanlp/Minerva-3B-base-v1.0" \
    --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": "sapienzanlp/Minerva-3B-base-v1.0",
		"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 "sapienzanlp/Minerva-3B-base-v1.0" \
        --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": "sapienzanlp/Minerva-3B-base-v1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use sapienzanlp/Minerva-3B-base-v1.0 with Ollama:
```
ollama run hf.co/sapienzanlp/Minerva-3B-base-v1.0
```

Unsloth Studio new

How to use sapienzanlp/Minerva-3B-base-v1.0 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for sapienzanlp/Minerva-3B-base-v1.0 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for sapienzanlp/Minerva-3B-base-v1.0 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for sapienzanlp/Minerva-3B-base-v1.0 to start chatting

Docker Model Runner
How to use sapienzanlp/Minerva-3B-base-v1.0 with Docker Model Runner:
```
docker model run hf.co/sapienzanlp/Minerva-3B-base-v1.0
```

Lemonade

How to use sapienzanlp/Minerva-3B-base-v1.0 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull sapienzanlp/Minerva-3B-base-v1.0

Run and chat with the model

lemonade run user.Minerva-3B-base-v1.0-{{QUANT_TAG}}

List all available models

lemonade list

Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Model Card for Minerva-3B-base-v1.0

Minerva is the first family of LLMs pretrained from scratch on Italian developed by Sapienza NLP in collaboration with Future Artificial Intelligence Research (FAIR) and CINECA. Notably, the Minerva models are truly-open (data and model) Italian-English LLMs, with approximately half of the pretraining data including Italian text.

Minerva LLMs - website

Description

This is the model card for Minerva-3B-base-v1.0, a 3 billion parameter model trained on 660 billion tokens (330 billion in Italian, 330 billion in English).

This model is part of the Minerva LLM family:

🚨⚠️🚨 Bias, Risks, and Limitations 🚨⚠️🚨

This section identifies foreseeable harms and misunderstandings.

This is a foundation model, not subject to alignment. Model may:

Overrepresent some viewpoints and underrepresent others
Contain stereotypes
Contain personal information
Generate:
- Racist and sexist content
- Hateful, abusive, or violent language
- Discriminatory or prejudicial language
- Content that may not be appropriate for all settings, including sexual content
Make errors, including producing incorrect information or historical facts as if it were factual
Generate irrelevant or repetitive outputs

We are aware of the biases and potential problematic/toxic content that current pretrained large language models exhibit: more specifically, as probabilistic models of (Italian and English) languages, they reflect and amplify the biases of their training data. For more information about this issue, please refer to our survey:

Biases in Large Language Models: Origins, Inventory, and Discussion

How to use Minerva with Hugging Face transformers

import transformers
import torch

model_id = "sapienzanlp/Minerva-3B-base-v1.0"

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

# Input text for the model.
input_text = "La capitale dell'Italia è"

# Compute the outputs.
output = pipeline(
  input_text,
  max_new_tokens=128,
)

# Output:
# [{'generated_text': "La capitale dell'Italia è la città di Roma, che si trova a [...]"}]

Model Architecture

Minerva-3B-base-v1.0 is a Transformer model based on the Mistral architecture, where the number of layers, number of heads, and the hidden states dimension are modified to reach 3B parameters. Please, take a look at the configuration file for a detailed breakdown of the hyperparameters we chose for this model.

The Minerva LLM family is composed of:

Model Name	Tokens	Layers	Hidden Size	Attention Heads	KV Heads	Sliding Window	Max Context Length
Minerva-350M-base-v1.0	70B (35B it + 35B en)	16	1152	16	4	2048	16384
Minerva-1B-base-v1.0	200B (100B it + 100B en)	16	2048	16	4	2048	16384
Minerva-3B-base-v1.0	660B (330B it + 330B en)	32	2560	32	8	2048	16384

Model Training

Minerva-3B-base-v1.0 was trained using llm-foundry 0.6.0 from MosaicML. The hyperparameters used are the following:

Model Name	Optimizer	lr	betas	eps	Scheduler	Warmup Steps	Batch Size (Tokens)	Total Steps
Minerva-350M-base-v1.0	Decoupled AdamW	2e-4	(0.9, 0.95)	1e-8	Cosine	2%	4M	16,690
Minerva-1B-base-v1.0	Decoupled AdamW	2e-4	(0.9, 0.95)	1e-8	Cosine	2%	4M	47,684
Minerva-3B-base-v1.0	Decoupled AdamW	2e-4	(0.9, 0.95)	1e-8	Cosine	2%	4M	157,357

Model Evaluation

We assessed our model using the LM-Evaluation-Harness library, which serves as a comprehensive framework for testing generative language models across a wide range of evaluation tasks.

All the reported benchmark data was already present in the LM-Evaluation-Harness suite.

Italian Data:

Task	Accuracy
xcopa (0-shot)	0.694
Hellaswag (5-shot)	0.5293
Belebele (5-shot)	0.2333
TruthfulQA MC 1 (0-shot)	0.2363
TruthfulQA MC 2 (0-shot)	0.3731
M MMLU (5-shot)	0.2612
arc challenge (5-shot)	0.3268

English Data:

Task	Accuracy
Hellaswag (5-shot)	0.6168
piqa (5-shot)	0.7535
sciq (5-shot)	0.925
Belebele (5-shot)	0.2278
TruthfulQA MC 1 (0-shot)	0.2142
TruthfulQA MC 2 (0-shot)	0.3643
M MMLU (5-shot)	0.263
arc challenge (5-shot)	0.3319
arc easy (5-shot)	0.6540

Training Data

Minerva-3B-base-v1.0 was trained on 330B Italian tokens and 330B English tokens sampled from CulturaX.

We have extracted some statistics on Italian (115B tokens) and English (210B tokens) documents from CulturaX on the selected sources:

Proportion of number of tokens per domain (Italian) italian-tok-counts

Proportion of number of tokens per domain (English) english-tok-counts

Tokenizer Fertility

The tokenizer fertility measures the average amount of tokens produced per tokenized word. A tokenizer displaying high fertility values in a particular language typically indicates that it segments words in that language extensively. The tokenizer fertility is strictly correlated with the inference speed of the model with respect to a specific language, as higher values mean longer sequences of tokens to generate and thus lower inference speed.

Fertility computed over a sample of Cultura X (CX) data and Wikipedia (Wp):

Model	Voc. Size	Fertility IT (CX)	Fertility EN (CX)	Fertility IT (Wp)	Fertility EN (Wp)
Mistral-7B-v0.1	32000	1.87	1.32	2.05	1.57
gemma-7b	256000	1.42	1.18	1.56	1.34
Minerva-3B-base-v1.0	32768	1.39	1.32	1.66	1.59

Notice

Minerva-3B-base-v1.0 is a pretrained base model and, therefore, has no moderation mechanisms.

The Sapienza NLP Team

Riccardo Orlando: data preprocessing, model training
Pere-Lluis Huguet Cabot: data preprocessing, vocabulary, evaluation
Luca Moroni: data curation, data analysis, downstream tasks, evaluation
Simone Conia: data curation, evaluation, project supervision
Edoardo Barba: data preprocessing, downstream tasks, project supervision
Roberto Navigli: project lead and coordination

Special thanks for their support

Giuseppe Fiameni, Nvidia
Sergio Orlandini, CINECA

Acknowledgments

This work was funded by the PNRR MUR project PE0000013-FAIR. We acknowledge the CINECA award "IscB_medit" under the ISCRA initiative, for the availability of high performance computing resources and support.