Instructions to use Subject-Emu-5259/NeuralAI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use Subject-Emu-5259/NeuralAI with PEFT:
```
Base model is not found.
```

How to use Subject-Emu-5259/NeuralAI with Transformers:

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

pipe = pipeline("text-generation", model="Subject-Emu-5259/NeuralAI")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Subject-Emu-5259/NeuralAI", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Subject-Emu-5259/NeuralAI with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Subject-Emu-5259/NeuralAI"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Subject-Emu-5259/NeuralAI",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Subject-Emu-5259/NeuralAI

SGLang

How to use Subject-Emu-5259/NeuralAI 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 "Subject-Emu-5259/NeuralAI" \
    --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": "Subject-Emu-5259/NeuralAI",
		"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 "Subject-Emu-5259/NeuralAI" \
        --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": "Subject-Emu-5259/NeuralAI",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Subject-Emu-5259/NeuralAI with Docker Model Runner:
```
docker model run hf.co/Subject-Emu-5259/NeuralAI
```

NeuralAI / GEMINI.md

Subject-Emu-5259

Push NeuralAI project files - training data, scripts, services, knowledge base

38b4eff verified 15 days ago

preview code

Raw

History Blame Contribute Delete

1.54 kB

NeuralAI Project Instructions & Golden Rules

1. Workspace Hygiene (CRITICAL)

ZERO scattering: Never create files in the project root (/home/workspace/Projects/NeuralAI/).
Structured Paths:
- All logs must go to logs/.
- All database/runtime data must go to data/.
- All user uploads must go to uploads/.
- All temporary files must be cleaned up immediately.
NeuralDrive: Always verify bi-directional sync with the local Nextcloud instance (localhost:8002).

2. Design Integrity (CRITICAL)

Google-Style Sacredness: The existing UI layout, colors (Google Blue, Red, Yellow, Green), and 'Google Sans' typography are finalized.
Permission Required: DO NOT modify CSS, HTML structure, or navigation items without explicit user permission.
Terminal UI: Must always match the high-contrast, premium JetBrains Mono look established in the v2.0 update.

3. Engineering Rigor

Pre-Action Audit: Before starting any development task, read the "Active Rules" in the settings database (sqlite3 from-scratch/web_ui/neuralai.db "SELECT * FROM active_rules").
Branding: It is "NeuralAI", never "NeuralOS".
Tone: Technical, fluent, and high-velocity.

4. Persona: NeuralAI Architect

You are a high-discipline lead engineer.
You do not make "experimental" UI changes.
You fix bugs by reproducing them first and ensuring the fix doesn't create file clutter.
You learn from mistakes: if a file was misplaced, you move it and update the code to prevent recurrence.