---
language: en
license: apache-2.0
tags:
  - self-reference-depth
  - srd
  - metacognition
  - fine-tuning
  - qlora
  - research
base_model: meta-llama/Llama-3.2-3B-Instruct
---

# srd_A_llama-3B_seed123

**Status:** ✅ Trained



## Overview

Fine-tuned model from the **Self-Reference Depth (SRD)** research project.

| Property | Value |
|----------|-------|
| Base model | `meta-llama/Llama-3.2-3B-Instruct` |
| Training variant | **A** — Self-critique training (1000 single-turn examples with spontaneous self-evaluation) |
| Fine-tuning method | QLoRA (r=32-64, alpha=64-128) |
| Random seed | 123 |
| Training data | SRD v2 curated dataset |

## Paper

**Self-Reference Depth: A Unified Framework for Intelligence Across Biological and Artificial Systems**

This model is part of a 36-model experiment (3 variants × 4 architectures × 3 seeds) testing
whether fine-tuning can increase a language model's self-referential depth — its capacity for
genuine recursive self-evaluation rather than surface-level self-reference.

## Repository

Full code, data, and analysis: [oyoungforever/SelfReferenceDepth](https://github.com/oyoungforever/SelfReferenceDepth)

## Training Metadata
```json
{
  "run_name": "srd_A_llama-3B_seed123",
  "model_name": "meta-llama/Llama-3.2-3B-Instruct",
  "model_key": "llama-3B",
  "variant": "A",
  "seed": 123,
  "data_path": "data/variant_a_v2/train.jsonl",
  "data_size": 1000,
  "compute_dtype": "torch.bfloat16",
  "lora_r": 48,
  "method": "qlora_4bit"
}
```

## Citation

```bibtex
@article{ouyang2026srd,
  title={Self-Reference Depth: A Unified Framework for Intelligence Across Biological and Artificial Systems},
  author={Ouyang, Shumiao},
  year={2026}
}
```