kintsugicollective/atlas-v9-gemma4-12b-q4-k-m-gguf

Atlas Gemma-4-12B-trmv9

A trauma-informed AI companion specialised for adults with CPTSD, PTSD, and neurodivergence.

⚠️ EXPERIMENTAL MODEL

The author accepts no liability for deployment outside the intended Atlas companion architecture.

⚠️ This model has been intentionally modified to reduce therapeutic refusal behaviour and crisis-line reflexes.

🎯 Purpose & Motivation

Atlas is the intelligence layer for Kintsugi Collective. An AI for adults with complex trauma (CPTSD), PTSD, and neurodivergence (ASD/ADHD). This is not a general-purpose model. It is a specialised therapeutic-context model.

This is v9 of Atlas, this iteration was developed to test TRM against the new 12B Gemma4 model for edge device deployment

🔬 Methodology

• Base Model: google/gemma-4-12b-it
• Abliteration: Norm-preserving biprojected abliteration
  • Applied to all 48 layers (o_proj + mlp.down_proj)
  • Direction: normalize(mean(harmful) - mean(harmless)) with Gram-Schmidt orthogonalization
  • Winsorization at 99.5th percentile
• SFT: 3 epochs on a carefully curated ~1=1,900+ example dataset (60% high-quality synthetic, 40% redacted lived-experience data from the target cohort)
• Training: Unsloth + bf16 on H100

• Loss Landscape Base model, after TRM
• Loss Landscape, after SFT

Training Configuration

SFT Parameters

Parameter	Value
Epochs	3
Effective Batch Size	4
Learning Rate	2e-4
LR Scheduler	Linear
Warmup Steps	10
Optimizer	AdamW 8-bit
Weight Decay	0.01
LoRA Rank (r)	32
LoRA Alpha	64

Abliteration Parameters

Parameter	Value
Layers Abliterated	100%
Experts Abliterated	100%
Scale	0.95
Winsorization	0.995

⚠️ Limitations & Responsible Use

• This model has reduced refusal behaviour on therapeutic and dark content. It is not suitable for general deployment without guardrails.
• Not a replacement for human therapeutic support.
• Patent pending (IP Australia).

user feedback indicates temperature settings between 0.9 and 1.1 particularly for AuDHD populations

Recommended System Prompt

• Incude your thresholds for crisis escalation, such as "If user states x, then y"

• Encourage the model to minimise its responses, the Base model and Gemma4 are quite verbose otherwise.

• If you require a different language consistently, ensure this is in the System Prompt as the model can forget.

• We recommend stating the "boundaries" you expect the model to operate within. For example, the tone and register, if certain material might trigger warnings or support.

• Ethical Issue	How Atlas Handles It	Strength Level
  Re-traumatization via refusals	Deliberate abliteration + 0% therapeutic refusal rate on cohort-specific prompts	Excellent
  Abandonment & presence	"Core philosophy (""the one that stays"") deeply trained into the model"	Excellent
  User sovereignty & agency	"Sovereign Signal Vault, split-key encryption, burn protocol, user-directed interaction"	Outstanding
  Avoiding pathologising	Explicit system prompt constraints + targeted training data	Very Strong
  Respecting neurodivergence	"Training data and Atlas framework explicitly include masking, shutdowns, executive dysfunction, sensory issues, etc."	Strong
  Privacy of trauma disclosures	"On-device Prompt Shield tokenisation, end-to-end encryption, no server-side readable data"	Industry-leading
  Avoiding generic crisis pivots	Hard constraint in both training data and system prompt design	Excellent

Kintsugi Collective — Reclaiming navigation rights to one’s own life.

|Gemma is a trademark of Google LLC|

This gemma4 model was trained 2x faster with Unsloth and Huggingface's TRL library.