vectrayx-pro-3b

VectraYX-Pro 3B

VectraYX-Pro 3B is a LoRA-64 adapter for Qwen2.5-3B-Instruct fine-tuned on the VectraYX Spanish cybersecurity SFT corpus (~93,500 examples). It is part of the VectraYX model family presented in the paper arXiv:2605.13989.

This repo contains only the LoRA adapter weights (~457 MB). You need to load them on top of Qwen/Qwen2.5-3B-Instruct.

• Paper: VectraYX-Nano arXiv:2605.13989
• Nano 42M (from-scratch headline model): jsantillana/vectrayx-nano
• Base 260M: jsantillana/vectrayx-base
• Pro 7B: jsantillana/vectrayx-pro-7b

---

Results (VectraYX-Bench, single seed)

---

What is this?

This adapter applies the VectraYX cybersecurity specialization to Qwen2.5-3B-Instruct:

• SFT corpus: ~93,500 examples — 13K OASST1-ES conversational + 4K CVE Q&A + 2.8K MCP tool-use traces + general cybersecurity Q&A
• Training: LoRA rank=64, 3 epochs, lr=2e-4 on AWS SageMaker (ml.g5.xlarge)
• Language: Spanish (LATAM-focused)
• Tool use: Native MCP <|tool_call|> emission (B4=0.600)
• Author website: https://jsantillana.com

---

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load base Qwen model (requires ~6 GB VRAM for bfloat16)
base_model = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen2.5-3B-Instruct",
    torch_dtype="auto",
    device_map="auto"
)

# Load VectraYX LoRA adapter on top
model = PeftModel.from_pretrained(base_model, "jsantillana/vectrayx-pro-3b")
tokenizer = AutoTokenizer.from_pretrained("jsantillana/vectrayx-pro-3b")

# Inference
messages = [{"role": "user", "content": "¿Qué es el CVE-2021-44228 y cuál es su severidad?"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=200, temperature=0.7)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Merge adapter into base (for export / GGUF)

merged = model.merge_and_unload()
merged.save_pretrained("vectrayx-pro-3b-merged")
tokenizer.save_pretrained("vectrayx-pro-3b-merged")

---

Model family

*Base 260M with LoRA-16 at ratio 1:21 achieves B4=0.445±0.201.

---

Citation

@misc{santillana2026vectrayx,
  title     = {VectraYX-Nano: A 42M-Parameter Spanish Cybersecurity Language Model
               with Curriculum Learning and Native Tool Use},
  author    = {Santillana, Juan S.},
  year      = {2026},
  eprint    = {2605.13989},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CL},
  url       = {https://arxiv.org/abs/2605.13989}
}