Instructions to use MagistrTheOne/NULLXES-OBSIDIAN-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MagistrTheOne/NULLXES-OBSIDIAN-v1 with Transformers:

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

pipe = pipeline("text-generation", model="MagistrTheOne/NULLXES-OBSIDIAN-v1")
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("MagistrTheOne/NULLXES-OBSIDIAN-v1")
model = AutoModelForImageTextToText.from_pretrained("MagistrTheOne/NULLXES-OBSIDIAN-v1")
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

vLLM

How to use MagistrTheOne/NULLXES-OBSIDIAN-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MagistrTheOne/NULLXES-OBSIDIAN-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MagistrTheOne/NULLXES-OBSIDIAN-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MagistrTheOne/NULLXES-OBSIDIAN-v1

SGLang

How to use MagistrTheOne/NULLXES-OBSIDIAN-v1 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 "MagistrTheOne/NULLXES-OBSIDIAN-v1" \
    --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": "MagistrTheOne/NULLXES-OBSIDIAN-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "MagistrTheOne/NULLXES-OBSIDIAN-v1" \
        --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": "MagistrTheOne/NULLXES-OBSIDIAN-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MagistrTheOne/NULLXES-OBSIDIAN-v1 with Docker Model Runner:
```
docker model run hf.co/MagistrTheOne/NULLXES-OBSIDIAN-v1
```

NULLXES VERIDIAN

Enterprise-grade AI Digital Employee Core.

Overview

NULLXES VERIDIAN is a next-generation cognitive system designed to operate as a real-time digital employee.

It combines conversational intelligence, structured execution, and decision routing into a unified AI layer for enterprise workflows.

Key Principles

Deterministic execution when required
Adaptive conversational behavior
Structured outputs for integration
Mode-based cognitive routing

Cognitive Architecture

VERIDIAN operates through internal routing between modes:

Chat Mode — natural human interaction
Action Mode — strict structured execution (JSON)
Coding Mode — deterministic code generation
Reasoning Mode — extended analysis and decision support

Routing is dynamically selected based on user intent and task complexity.

Capabilities

Real-time conversational interface
Structured task execution
Workflow orchestration
Code generation and automation
Context-aware reasoning

Use Cases

Digital employees for enterprise operations
AI-powered task automation
Business process augmentation
Developer copilots and internal tools
Real-time support systems

Integration

Designed for integration into:

internal enterprise systems
CRM / ERP workflows
real-time communication layers
API-based execution environments

Notes

NULLXES VERIDIAN is part of the NULLXES Digital Workforce Infrastructure.

It is intended to function not as a chatbot, but as an operational AI layer capable of executing real tasks within production environments.

Downloads last month: 235

Safetensors

Model size

35B params

Tensor type

F32

BF16