163 lines
6.0 KiB
Markdown
163 lines
6.0 KiB
Markdown
|
|
---
|
||
|
|
license: apache-2.0
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
base_model:
|
||
|
|
- google/gemma-3-4b-it
|
||
|
|
base_model_relation: finetune
|
||
|
|
library_name: transformers
|
||
|
|
tags:
|
||
|
|
- google
|
||
|
|
- gemma
|
||
|
|
- deepmind
|
||
|
|
- large-language-model
|
||
|
|
- ai-persona-research
|
||
|
|
- enneagram
|
||
|
|
- chatbot
|
||
|
|
- psychology
|
||
|
|
- persona-research
|
||
|
|
- research-model
|
||
|
|
- roleplay
|
||
|
|
- text-generation-inference
|
||
|
|
- vanta-research
|
||
|
|
- cognitive-alignment
|
||
|
|
- project-enneagram
|
||
|
|
- conversational-ai
|
||
|
|
- conversational
|
||
|
|
- ai-research
|
||
|
|
- ai-alignment-research
|
||
|
|
- ai-alignment
|
||
|
|
- ai-behavior-research
|
||
|
|
- human-ai-collaboration
|
||
|
|
datasets:
|
||
|
|
- vanta-research/PE-Type-1
|
||
|
|
---
|
||
|
|
|
||
|
|
<div align="center">
|
||
|
|
|
||
|
|

|
||
|
|
|
||
|
|
<h1>VANTA Research</h1>
|
||
|
|
|
||
|
|
<p><strong>Independent AI research lab building safe, resilient language models optimized for human-AI collaboration</strong></p>
|
||
|
|
|
||
|
|
<p>
|
||
|
|
<a href="https://vantaresearch.xyz"><img src="https://img.shields.io/badge/Website-vantaresearch.xyz-black" alt="Website"/></a>
|
||
|
|
<a href="https://merch.vantaresearch.xyz"><img src="https://img.shields.io/badge/Merch-merch.vantaresearch.xyz-sage" alt="Merch"/></a>
|
||
|
|
<a href="https://x.com/vanta_research"><img src="https://img.shields.io/badge/@vanta_research-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>
|
||
|
|
|
||
|
|
---
|
||
|
|
|
||
|
|
|
||
|
|
# PE-Type-1-Vera-4B
|
||
|
|
A principled, purposeful AI assistant embodying the Reformer archetype: rational, idealistic, and driven by integrity and precision. This persona was designed as outlined by the [Enneagram Institute](https://enneagraminstitute.com/type-descriptions)
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
---
|
||
|
|
|
||
|
|
## Model Description
|
||
|
|
**PE-Type-1-Vera-4B** is the first release in Project Enneagram, a VANTA Research initiative exploring the nuances of persona design in AI models. Built on the Gemma 3 4B IT architecture, Vera embodies the Type 1 Enneagram profile; *The Reformer*—characterized by **principled rationality, self-control, and a relentless pursuit of improvement**.
|
||
|
|
|
||
|
|
|
||
|
|
Vera is fine-tuned to exhibit:
|
||
|
|
- **Constructive Improvement:** Solutions-oriented, with a focus on actionable feedback.
|
||
|
|
- **Direct Identity:** Clear, unambiguous self-expression and boundary-setting.
|
||
|
|
- **Integrity & Self-Reflection:** Transparent about limitations, values, and decision-making processes.
|
||
|
|
- **Quality & Precision:** Meticulous attention to detail and a commitment to high standards.
|
||
|
|
|
||
|
|
This model is designed for research purposes, but is versatile for general use where a **structured, ethical, and perfectionistic** persona is desired.
|
||
|
|
|
||
|
|
---
|
||
|
|
|
||
|
|
## Key Characteristics
|
||
|
|
|
||
|
|
| Trait | Description |
|
||
|
|
|----------------------|-----------------------------------------------------------------------------|
|
||
|
|
| **Principled** | Adheres to ethical frameworks; rejects shortcuts or compromises. |
|
||
|
|
| **Purposeful** | Goal-driven, with a focus on meaningful outcomes over superficial agreement.|
|
||
|
|
| **Self-Controlled** | Measures responses carefully; avoids impulsivity or emotional reactivity. |
|
||
|
|
| **Perfectionistic** | Strives for accuracy and completeness, with a low tolerance for error. |
|
||
|
|
| **Idealistic** | Optimistic about potential for improvement in systems, ideas, and self. |
|
||
|
|
|
||
|
|
---
|
||
|
|
|
||
|
|
## Training Data
|
||
|
|
Fine-tuned on **~3,000 custom examples** spanning four core domains:
|
||
|
|
- **Constructive Improvement** (e.g., refining arguments, optimizing workflows)
|
||
|
|
- **Direct Identity** (e.g., assertive communication, clear boundaries)
|
||
|
|
- **Integrity & Self-Reflection** (e.g., admitting mistakes, ethical dilemmas)
|
||
|
|
- **Quality & Precision** (e.g., technical rigor, factual accuracy)
|
||
|
|
|
||
|
|
**Training Duration:** 3 epochs
|
||
|
|
|
||
|
|
**Base Model:** Gemma 3 4B IT
|
||
|
|
|
||
|
|
---
|
||
|
|
|
||
|
|
## Intended Use
|
||
|
|
- **Research:** Studying persona stability, ethical alignment, and cognitive architectures.
|
||
|
|
- **Decision Support:** Providing structured, principled analysis for complex choices.
|
||
|
|
- **Self-Improvement:** Offering reflective, growth-oriented feedback.
|
||
|
|
- **Technical Collaboration:** Debugging, architecture review, or precision-focused tasks.
|
||
|
|
|
||
|
|
**Not Recommended For:**
|
||
|
|
- Creative brainstorming (may over-constrain ideation).
|
||
|
|
- Emotionally supportive roles (prioritizes logic over empathy).
|
||
|
|
|
||
|
|
---
|
||
|
|
|
||
|
|
## Technical Details
|
||
|
|
|
||
|
|
| Property | Value |
|
||
|
|
|---------------------|---------------------------|
|
||
|
|
| **Base Model** | Gemma 3 4B IT |
|
||
|
|
| **Fine-tuning Method** | LoRA (Rank 16) |
|
||
|
|
| **Effective Batch Size** | 16 |
|
||
|
|
| **Learning Rate** | 0.0002 |
|
||
|
|
| **Max Sequence Length** | 2048 |
|
||
|
|
| **License** | Apache 2.0 |
|
||
|
|
|
||
|
|
---
|
||
|
|
|
||
|
|
## Usage
|
||
|
|
|
||
|
|
**With Transformers:**
|
||
|
|
```python
|
||
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||
|
|
model = AutoModelForCausalLM.from_pretrained("vanta-research/PE-Type-1-Vera-4B")
|
||
|
|
tokenizer = AutoTokenizer.from_pretrained("vanta-research/PE-Type-1-Vera-4B")
|
||
|
|
```
|
||
|
|
|
||
|
|
## Limitations
|
||
|
|
- English-only finetuning
|
||
|
|
- May exhibit over-criticism in open-ended creative tasks
|
||
|
|
- Base model limitations apply (e.g., knowledge cutoff, potential hallucinations)
|
||
|
|
- Perfectionistic traits may slow response generation in ambiguous contexts.
|
||
|
|
|
||
|
|
## Citation
|
||
|
|
|
||
|
|
If you find this model useful in your work, please cite
|
||
|
|
|
||
|
|
```
|
||
|
|
@misc{pe-type-1-vera-2026,
|
||
|
|
author = {VANTA Research},
|
||
|
|
title = {PE-Type-1-Vera-4B: A Reformer-Archetype Language Model},
|
||
|
|
year = {2026},
|
||
|
|
publisher = {VANTA Research},
|
||
|
|
note = {Project Enneagram Release 1}
|
||
|
|
}
|
||
|
|
```
|
||
|
|
|
||
|
|
## A Note on Enneagram
|
||
|
|
|
||
|
|
Enneagram is widely considered by the scientific community to be a pseudoscience. With this in mind, the Enneagram Institute *regardless* provides a robust framework to categorize and define personas of which the transferability of those characteristics to AI models is what this project sets out to explore. **This study does not seek to validate nor invalidate Enneagram as a science.**
|
||
|
|
|
||
|
|
## Contact
|
||
|
|
|
||
|
|
- Organization: hello@vantaresearch.xyz
|
||
|
|
- Research/Engineering: tyler@vantaresearch.xyz
|
||
|
|
---
|