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", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Subject-Emu-5259/NeuralAI")
model = AutoModelForCausalLM.from_pretrained("Subject-Emu-5259/NeuralAI", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

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 / docs /SOCIAL.md

Subject-Emu-5259

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

38b4eff verified 9 days ago

preview code

Raw

History Blame

2.11 kB

	# NeuralAI — Social Preview

	## GitHub Bio

	Custom AI assistant fine-tuned from SmolLM2-360M-Instruct. QLoRA training, RAG document search, integrated terminal, Neural Uplink agent network.

	## Repository Description

	NeuralAI is a production-ready AI assistant with a full-stack web UI, RAG document intelligence, integrated terminal, and Neural Uplink multi-agent routing. Built with SmolLM2-360M-Instruct + QLoRA fine-tuning.

	## Social Tags

	Title: NeuralAI — Custom LLM with RAG + Terminal + Neural Uplink

	Description: Production AI assistant with local LLM inference, document RAG (PDF/DOCX/TXT/MD), integrated terminal, and multi-agent Neural Uplink network. 360M parameters, CPU-ready.

	Keywords: neuralai, llm, fine-tuning, qlora, smollm2, pytorch, transformers, rag, vector-database, chromadb, terminal, agentic-ai, custom-ai, language-model, chat-assistant, local-ai

	## Repository Topics

	```markdown
	neuralai llm fine-tuning qlora smollm2 pytorch transformers rag chromadb terminal agentic-ai custom-ai language-model chat-assistant local-ai
	```

	## Sample Tweet

	> Built my own AI assistant from scratch 🤖\
	> Features: RAG docs, integrated terminal, Neural Uplink agents.\
	> Fine-tuned SmolLM2-360M with QLoRA — all running locally on CPU.
	>
	> #AI #LLM #FineTuning #NeuralAI #Python #RAG

	## Sample LinkedIn Post

	> I just built my own production AI assistant.
	>
	> NeuralAI v2.4 is live with:
	>
	> - Local LLM: SmolLM2-360M-Instruct, fine-tuned with QLoRA
	> - RAG: PDF/DOCX/TXT/MD semantic search with ChromaDB
	> - Integrated Terminal: Persistent PTY shell with custom AI commands
	> - Neural Uplink: Baltimore node with 4 specialized AI agents
	>
	> 360M params, CPU-ready, runs anywhere.
	>
	> #MachineLearning #AI #Python #LLM #RAG

	## Thumbnail / Banner Concept

	- Left side: Neural network + terminal + document icons arranged as connected nodes
	- Right side: "NeuralAI" in bold, "RAG • Terminal • Neural Uplink" below
	- Accent color: Electric purple (#7c3aed) / cyan (#22d3ee) on dark background
	- Tagline: "Your AI. On your hardware. In your browser."