Instructions to use jsantillana/vectrayx-nano with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jsantillana/vectrayx-nano with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="jsantillana/vectrayx-nano",
	filename="vectrayx-nano-f16.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 jsantillana/vectrayx-nano with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf jsantillana/vectrayx-nano:F16
# Run inference directly in the terminal:
llama-cli -hf jsantillana/vectrayx-nano:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf jsantillana/vectrayx-nano:F16
# Run inference directly in the terminal:
llama-cli -hf jsantillana/vectrayx-nano:F16

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 jsantillana/vectrayx-nano:F16
# Run inference directly in the terminal:
./llama-cli -hf jsantillana/vectrayx-nano:F16

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 jsantillana/vectrayx-nano:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jsantillana/vectrayx-nano:F16

Use Docker

docker model run hf.co/jsantillana/vectrayx-nano:F16

LM Studio
Jan

vLLM

How to use jsantillana/vectrayx-nano with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/jsantillana/vectrayx-nano:F16

Ollama
How to use jsantillana/vectrayx-nano with Ollama:
```
ollama run hf.co/jsantillana/vectrayx-nano:F16
```

Unsloth Studio new

How to use jsantillana/vectrayx-nano 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 jsantillana/vectrayx-nano 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 jsantillana/vectrayx-nano to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for jsantillana/vectrayx-nano to start chatting

Docker Model Runner
How to use jsantillana/vectrayx-nano with Docker Model Runner:
```
docker model run hf.co/jsantillana/vectrayx-nano:F16
```

Lemonade

How to use jsantillana/vectrayx-nano with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jsantillana/vectrayx-nano:F16

Run and chat with the model

lemonade run user.vectrayx-nano-F16

List all available models

lemonade list

Add pipeline tag and links to paper and code

by nielsr HF Staff - opened 8 days ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+13

-11

Files changed (1) hide show

README.md +13 -11

README.md CHANGED Viewed

@@ -1,7 +1,13 @@
 ---
 language:
 - es
 license: apache-2.0
 tags:
 - cybersecurity
 - spanish
@@ -9,17 +15,14 @@ tags:
 - mcp
 - curriculum-learning
 - from-scratch
-datasets:
-- vectrayx/vectrayx-bench
-metrics:
-- accuracy
-- f1
 ---
 # VectraYX-Nano
-A 42M-parameter Spanish cybersecurity language model trained from scratch with
-curriculum learning and native MCP tool use.
 ## Key Results (VectraYX-Bench)
@@ -40,10 +43,9 @@ Base 260M achieves B4=0.580.
 ## Usage
-```python
-# Load with custom inference script
-# See: https://huggingface.co/vectrayx/vectrayx-paper-code
 from huggingface_hub import hf_hub_download
 import torch
@@ -63,4 +65,4 @@ config_path = hf_hub_download("vectrayx/vectrayx-nano", "configs/nano.json")
   booktitle = {Preprint},
   year      = {2026}
 }
-```

 ---
+datasets:
+- vectrayx/vectrayx-bench
 language:
 - es
 license: apache-2.0
+metrics:
+- accuracy
+- f1
+pipeline_tag: text-generation
 tags:
 - cybersecurity
 - spanish
 - mcp
 - curriculum-learning
 - from-scratch
 ---
 # VectraYX-Nano
+VectraYX-Nano is a 42M-parameter Spanish cybersecurity language model trained from scratch with curriculum learning and native Model Context Protocol (MCP) tool use.
+- **Paper:** [VectraYX-Nano: A 42M-Parameter Spanish Cybersecurity Language Model with Curriculum Learning and Native Tool Use](https://huggingface.co/papers/2605.13989)
+- **Repository:** [vectrayx/vectrayx-nano-paper](https://github.com/vectrayx/vectrayx-nano-paper)
 ## Key Results (VectraYX-Bench)
 ## Usage
+To use this model, please refer to the custom inference scripts provided in the official [GitHub repository](https://github.com/vectrayx/vectrayx-nano-paper).
+```python
 from huggingface_hub import hf_hub_download
 import torch
   booktitle = {Preprint},
   year      = {2026}
 }
+```