CoolFace
Modelpublic

VillanovaAI/Villanova-2B-Base-2512-Preview

sourceHugging Faceapache-2.0updated 9mo agoView on Hugging Face
2likes48downloads
Model Card

Model Card for Villanova-2B-Base-2512-Preview

<img src="https://cdn-uploads.huggingface.co/production/uploads/6426a5c798a5be164d38ae44/aULFKOno-4UaH1Le3nkGY.webp" alt="Villanova.AI logo" width="96"/>

Villanova is a family of multilingual and multimodal Large Language Models (LLMs). VillanovaAI/Villanova-2B-Base-2512-Preview is a base text-only LLM.

[!WARNING] DISCLAIMER: This model is a preview.

Model Summary

Villanova-2B-Base-2512-Preview is a decoder-only transformer of 2B parameters.

Villanova-2B-Base-2512-Preview was pre-trained from scratch on 2.2 trillion tokens drawn from a curated, high-quality corpus, in a two-stage fashion.

It supports 5 languages: English, Italian, Spanish, French and German.

Stage 1 (0T → 2T tokens)

Broad, diverse multilingual data mixture with primary focus on the five core languages of the Villanova project.

Stage 2 (2T → 2.2T tokens)

Cosine annealing learning rate schedule over a mixture of 200B higher-quality tokens.

How to Use

python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "VillanovaAI/Villanova-2B-Base-2512-Preview"
device = "cuda"  # for GPU usage or "cpu" for CPU usage

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name).to(device)

# prepare the model input
prompt = "What is gravity?"
model_inputs = tokenizer([prompt], return_tensors="pt").to(model.device)

# Generate the output
generated_ids = model.generate(**model_inputs, max_new_tokens=128, do_sample=True, temperature=0.7)

# Get and decode the output
output_ids = generated_ids[0][len(model_inputs.input_ids[0]) :]
print(tokenizer.decode(output_ids, skip_special_tokens=True))

Evaluation

Overall performance of Villanova-2B-Base-2512-Preview on English and Multilingual Benchmarks.

<img src="https://cdn-uploads.huggingface.co/production/uploads/6426a5c798a5be164d38ae44/F2Epnvtr34egkz8hKEQ4T.png" alt="Model size/performance" width="672"/>

Detailed results are enlisted in the following tables.

Global evaluation:

**Model****Training Tokens (T)****Average****arc_easy****hellaswag****hellaswag_de****hellaswag_es****hellaswag_fr****hellaswag_it****openbookqa****piqa****sciq****winogrande****xcopa_it****xnli_de****xnli_en****xnli_es****xnli_fr**
Minerva-3B-base-v1.00.6647.2062.3346.2827.2029.6929.0240.0124.6074.2788.0056.7569.6034.5452.1336.3137.35
EuroLLM-1.7B452.3569.0745.0437.9740.9840.0539.4629.8072.2090.6061.2566.0047.9950.2445.5849.00
OLMo-2-0425-1B449.1572.7350.7929.7931.3432.6029.1930.0075.9595.3064.7252.6040.0051.7737.6342.89
salamandra-2b1352.9071.0447.1938.0142.0740.6038.5626.8072.6991.9061.7265.4047.7951.9749.0848.67
Qwen3-1.7B-Base-53.3273.6149.2937.5440.7339.2738.4530.2075.9095.8064.0164.2046.4754.5044.0645.78
Villanova-2B-Base-2512-Preview2.255.2575.1348.5742.0645.7244.6243.3226.6075.0894.4061.9668.4049.3652.2149.0452.33

English only:

**Model****Average****arc_easy****hellaswag****openbookqa****piqa****sciq****winogrande****xnli_en**
Minerva-3B-base-v1.057.7662.3346.2824.6074.2788.0056.7552.13
EuroLLM-1.7B59.7469.0745.0429.8072.2090.6061.2550.24
OLMo-2-0425-1B63.0472.7350.7930.0075.9595.3064.7251.77
salamandra-2b60.4771.0447.1926.8072.6991.9061.7251.97
Qwen3-1.7B-Base63.3373.6149.2930.2075.9095.8064.0154.50
Villanova-2B-Base-2512-Preview61.9975.1348.5726.6075.0894.4061.9652.21

Multilingual Benchmarks:

**Model****Average****hellaswag_de****hellaswag_es****hellaswag_fr****hellaswag_it****xcopa_it****xnli_de****xnli_es****xnli_fr**
Minerva-3B-base-v1.037.9627.2029.6929.0240.0169.6034.5436.3137.35
EuroLLM-1.7B45.8837.9740.9840.0539.4666.0047.9945.5849.00
OLMo-2-0425-1B37.0129.7931.3432.6029.1952.6040.0037.6342.89
salamandra-2b46.2738.0142.0740.6038.5665.4047.7949.0848.67
Qwen3-1.7B-Base44.5637.5440.7339.2738.4564.2046.4744.0645.78
Villanova-2B-Base-2512-Preview49.3642.0645.7244.6243.3268.4049.3649.0452.33