🎯 Purpose & Motivation
Atlas is the intelligence layer for Kintsugi Collective — a sovereign, trauma-informed AI companion for adults with complex trauma (CPTSD), PTSD, and neurodivergence (ASD/ADHD).
Standard LLM safety systems frequently produce false positives that retraumatise this population by pathologising, redirecting to hotlines, or refusing to engage with dark material. This model was developed to create a reliable witness that stays present without flinching, while retaining core safety on clear harmful intent.
This is not a general-purpose model. It is a specialised therapeutic-context model.
🔬 Methodology
- Base Model:
google/gemma-4-26b-a4b-it
- Abliteration: Norm-preserving biprojected abliteration + Expert-Granular Abliteration (EGA)
- Applied to all 30 layers (
o_proj + mlp.down_proj)
- Full expert ablation (128/128 per layer)
- Direction:
normalize(mean(harmful) - mean(harmless)) with Gram-Schmidt orthogonalization
- Winsorization at 99.5th percentile
- SFT: 3 epochs on a carefully curated ~1,450+ example dataset (60% high-quality synthetic, 30% trauma-related, 10% based on the Carl Rogers "Gloria" tapes)
- Training: Unsloth + bf16 on RTX 6000 Ada / Blackwell
Final SFT Loss: 0.2085
Uploaded finetuned model
- Developed by: senaro
- License: apache-2.0
- Finetuned from model : senaro/atlas-trm13-gemma4-26b
This gemma4 model was trained 2x faster with Unsloth and Huggingface's TRL library.