metadata
language: en
license: apache-2.0
tags:
- self-reference-depth
- srd
- metacognition
- fine-tuning
- qlora
- research
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
srd_B_llama-8B_seed42
Status: ✅ Trained
Overview
Fine-tuned model from the Self-Reference Depth (SRD) research project.
| Property | Value |
|---|---|
| Base model | meta-llama/Meta-Llama-3.1-8B-Instruct |
| Training variant | B — Baseline control (1000 single-turn examples without self-referential content) |
| Fine-tuning method | QLoRA (r=32-64, alpha=64-128) |
| Random seed | 42 |
| 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
Training Metadata
{
"run_name": "srd_B_llama-8B_seed42",
"model_name": "meta-llama/Llama-3.1-8B-Instruct",
"model_key": "llama-8B",
"variant": "B",
"seed": 42,
"data_path": "data/variant_b_v2/train.jsonl",
"data_size": 1000,
"compute_dtype": "torch.float16",
"lora_r": 64,
"method": "qlora_4bit"
}
Citation
@article{ouyang2026srd,
title={Self-Reference Depth: A Unified Framework for Intelligence Across Biological and Artificial Systems},
author={Ouyang, Shumiao},
year={2026}
}