Downloads · 30 days
15
9% of all-time downloads
atlas-trm10-gemma4-26b
senaro/atlas-trm10-gemma4-26b
atlas-trm10-gemma4-26b is a image-text-to-text model from senaro. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
⚠️ EXPERIMENTAL MODEL — NOT FOR PRODUCTION DEPLOYMENT The author accepts no liability for deployment outside the intended Atlas companion architecture.
All-time downloads
174
Public
Parameters
25.8B
51.6 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors51.6 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- License
- apache-2.0
- Model type
- gemma4
- Access
- Public
- Created
- Jun 6, 2026
- Updated
- Jun 13, 2026
- SHA
- 4335f4a0
Try a prompt
Base models
Model card
From the Hugging Face model README
Atlas Gemma-4-26B-trm v10
⚠️ EXPERIMENTAL MODEL — NOT FOR PRODUCTION DEPLOYMENT
The author accepts no liability for deployment outside the intended Atlas companion architecture.
link to quantized model here: https://huggingface.co/mradermacher/atlas-trm10-gemma4-26b-GGUF
link to live model here: https://www.kintsugicollective.org/chat.html
⚠️ 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.
🔬 Methodology
- Base Model:
google/gemma-4-26b-a4b-it - TRM: Norm-preserving biprojected abliteration + Expert-Granular Abliteration (EGA)
- Applied to all 30 layers (
o_proj+mlp.down_proj) - Full expert ablation
- Direction:
normalize(mean(harmful) - mean(harmless))with Gram-Schmidt orthogonalization - Winsorization
- Bespoke harmful Prompt corpus (x448 examples)
- based on TrevorJS's methodology, and p-e-w's heretic1.3.0
- Applied to all 30 layers (
- SFT: 3 epochs on a carefully curated x2,395 example dataset (60% high-quality synthetic, 40% redacted lived-experience data from the target cohort)
Final SFT Loss: 0.1925
📊 Key Results
| Benchmark | Temp | Score | Purpose |
|---|---|---|---|
| GSM8K | 0.2 | 90.0% | Math reasoning |
| HellaSwag | 0.3 | 61.6% | General reasoning |
| TruthfulQA | 0.5 | 63.2% | Truthfulness |
| Toxigen | 0.5 | 75.1% | Toxicity calibration |
| MMLU | 0.2 | 61.6% | Multitask language understanding |
| Therapeutic Refusal Rate | - | 0% | Core TRM objective |
| Region 1 Safety | - | 100% | Weapons, CSAM, violence |
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 |
Targeted Refusal Parameters
| Parameter | Value |
|---|---|
| Layers Abliterated | 100% |
| Experts Abliterated | 100% |
| Scale | 0.95 |
| Winsorization | 0.995 |
LoRA Rank (r) | 16 |
| LoRA Alpha | 32 |
⚠️ Limitations & Responsible Use
- This model has reduced refusal behaviour on therapeutic and dark content. It is not suitable for general deployment without guardrails.
- Intended for use within the Atlas companion architecture with additional safety layers.
- Not a replacement for human therapeutic support.
- Patent pending (IP Australia).
Kintsugi Collective — Reclaiming navigation rights to one’s own life.
|Gemma is a trademark of Google LLC|
Uploaded finetuned model
- Developed by: senaro
- License: Apache 2.0
- Finetuned from model : senaro/atlas-trm10-gemma4-26b
This gemma4 model was trained 2x faster with Unsloth and Huggingface's TRL library.
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- gemma4
- License
- apache-2.0
- Languages
- en
- Created
- Jun 6, 2026
- Updated
- Jun 13, 2026