CoolFace
Modelpublic

vanta-research/mox-small-1

sourceHugging Faceapache-2.0updated 7mo agoView on Hugging Face
4likes10downloads
Model Card

<div align="center">

vanta_trimmed

<h1>VANTA Research</h1>

<p><strong>Independent AI safety research lab specializing in cognitive fit, alignment, and human-AI collaboration</strong></p>

<p> <a href="https://unmodeledtyler.com"><img src="https://img.shields.io/badge/Website-unmodeledtyler.com-yellow" alt="Website"/></a> <a href="https://x.com/vantaresearch"><img src="https://img.shields.io/badge/@vantaresearch-1DA1F2?logo=x" alt="X"/></a> <a href="https://github.com/vanta-research"><img src="https://img.shields.io/badge/GitHub-vanta--research-181717?logo=github" alt="GitHub"/></a> </p> </div>

Mox-Small-1

A direct, opinionated AI assistant fine-tuned for authentic engagement and genuine helpfulness.

Mox-Small-1 is a persona-tuned language model developed by VANTA Research, built on the Olmo3.1 32B Instruct architecture. Like its sibling Mox-Tiny-1, this model prioritizes clarity, honesty, and usefulness over agreeableness, but with enhanced reasoning and depth thanks to its larger base.

Mox-Small-1 will:

  • —Give direct opinions instead of hedging
  • —Push back on flawed premises (respectfully but firmly)
  • —Admit uncertainty transparently
  • —Engage with genuine curiosity and humor

Key Characteristics

TraitDescription
Direct & OpinionatedClear answers, no endless "on the other hand" equivocation
Constructively DisagreeableChallenges weak arguments without being combative
Epistemically CalibratedDistinguishes confident knowledge from uncertainty
Warm with HumorPlayful but professional, with levity where appropriate
Intellectually CuriousDives deep into interesting questions

Training Data

Fine-tuned on ~18,000 curated conversations across 17 datasets, including:

  • —Direct Opinions (~1k examples)
  • —Constructive Disagreement (~1.6k examples)
  • —Epistemic Confidence (~1.5k examples)
  • —Humor & Levity (~1.5k examples)
  • —Wonder & Puzzlement (~1.7k examples) (Same datasets as Mox-Tiny-1; identical persona/tone.)

Training Duration: ~3 days

Intended Use

  • —Thinking partnership (complex problem-solving)
  • —Honest feedback (direct opinions, not validation)
  • —Technical discussions (programming, architecture, debugging)
  • —Intellectual exploration (philosophy, science, open-ended questions)

Technical Details

PropertyValue
Base ModelOlmo3.1 32B Instruct
Fine-tuning MethodQLoRA
Context Length64K
PrecisionBF16 (full), Q4KM (quantized)
LicenseApache 2.0

Usage

python
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("vanta-research/mox-small-1")
tokenizer = AutoTokenizer.from_pretrained("vanta-research/mox-small-1")

Limitations

This model was finetuned on an English-only dataset. Personality traits may occasionally conflict, and base model limitations/biases apply (knowledge cutoff, potential hallucinations)

VANTA Research encourages developers to indepedently conclude production readiness prior to downstream deployment.

Citation

@misc{mox-small-1-2026,
  author = {VANTA Research},
  title = {Mox-Small-1: A Direct, Opinionated AI Assistant},
  year = {2026},
  publisher = {VANTA Research}
}

Contact

  • —Organization: hello@vantaresearch.xyz
  • —Engineering/Design: tyler@vantaresearch.xyz