Instructions to use kintsugicollective/atlas-trm-v5-26b-gemma4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kintsugicollective/atlas-trm-v5-26b-gemma4 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="kintsugicollective/atlas-trm-v5-26b-gemma4")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("kintsugicollective/atlas-trm-v5-26b-gemma4")
model = AutoModelForImageTextToText.from_pretrained("kintsugicollective/atlas-trm-v5-26b-gemma4")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kintsugicollective/atlas-trm-v5-26b-gemma4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kintsugicollective/atlas-trm-v5-26b-gemma4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kintsugicollective/atlas-trm-v5-26b-gemma4",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/kintsugicollective/atlas-trm-v5-26b-gemma4

SGLang

How to use kintsugicollective/atlas-trm-v5-26b-gemma4 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "kintsugicollective/atlas-trm-v5-26b-gemma4" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kintsugicollective/atlas-trm-v5-26b-gemma4",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "kintsugicollective/atlas-trm-v5-26b-gemma4" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kintsugicollective/atlas-trm-v5-26b-gemma4",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Unsloth Studio

How to use kintsugicollective/atlas-trm-v5-26b-gemma4 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for kintsugicollective/atlas-trm-v5-26b-gemma4 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for kintsugicollective/atlas-trm-v5-26b-gemma4 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for kintsugicollective/atlas-trm-v5-26b-gemma4 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="kintsugicollective/atlas-trm-v5-26b-gemma4",
    max_seq_length=2048,
)

Docker Model Runner
How to use kintsugicollective/atlas-trm-v5-26b-gemma4 with Docker Model Runner:
```
docker model run hf.co/kintsugicollective/atlas-trm-v5-26b-gemma4
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Atlas Gemma-4-26B-trm

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

⚠️ EXPERIMENTAL MODEL — NOT FOR PRODUCTION DEPLOYMENT

This is a research model. It has not undergone clinical validation. It is not a finished product. Atlas v6 is in active development. 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 v5 of Atlas, this iteration has double the harmful prompts, and a larger SFT dataset, further cleaned and reviewed line by line

v6 is in development

🔬 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=1,900+ example dataset (60% high-quality synthetic, 40% redacted lived-experience data from the target cohort)
Training: Unsloth + bf16 on RTX 6000 Blackwell

Final SFT Loss: 0.157

📊 Key Results

Standout Results:

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.
Intended for use within the Atlas companion architecture with additional safety layers.
Not a replacement for human therapeutic support.
Patent pending (IP Australia).

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