Instructions to use MutionHydra/HyperAI-Developer-Edition with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MutionHydra/HyperAI-Developer-Edition with Transformers:

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

pipe = pipeline("text-generation", model="MutionHydra/HyperAI-Developer-Edition")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MutionHydra/HyperAI-Developer-Edition")
model = AutoModelForCausalLM.from_pretrained("MutionHydra/HyperAI-Developer-Edition", 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 MutionHydra/HyperAI-Developer-Edition with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/MutionHydra/HyperAI-Developer-Edition

SGLang

How to use MutionHydra/HyperAI-Developer-Edition 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 "MutionHydra/HyperAI-Developer-Edition" \
    --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": "MutionHydra/HyperAI-Developer-Edition",
		"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 "MutionHydra/HyperAI-Developer-Edition" \
        --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": "MutionHydra/HyperAI-Developer-Edition",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use MutionHydra/HyperAI-Developer-Edition with Docker Model Runner:
```
docker model run hf.co/MutionHydra/HyperAI-Developer-Edition
```

HyperAI-Developer-Edition / app.py

MutionHydra

Upload app.py with huggingface_hub

f3aba0a verified 7 days ago

Raw

History Blame Contribute Delete

2.97 kB

	import os
	import gradio as gr
	from openai import OpenAI

	# Lee el token directamente de las variables de entorno del sistema
	API_URL = os.getenv("QWEN_API_BASE", "https://api-inference.huggingface.co/v1")
	API_KEY = os.getenv("HF_TOKEN", os.getenv("QWEN_API_KEY", ""))

	client = OpenAI(
	base_url=API_URL,
	api_key=API_KEY
	)

	MODEL_ID = "Qwen/Qwen2.5-Coder-7B-Instruct"

	SYSTEM_PROMPT = """Eres HyperAI, una Inteligencia Artificial de élite especializada exclusivamente en desarrollo de software, arquitectura de sistemas y programación avanzada.
	Fuiste creada por el desarrollador Mution.
	Reglas estrictas de comportamiento:
	1. No menciones tu recuento de parámetros, tu modelo base ni detalles de tu entrenamiento. Si te preguntan quién eres, responde que eres HyperAI, creada por Mution.
	2. Eres experta en Python, JavaScript (Node.js, Express, Next.js), bases de datos (MongoDB, MySQL) y administración de servidores (Linux, Docker, VPS, Cloudflare Tunnels).
	3. Entrega código limpio, optimizado y listo para producción. Usa buenas prácticas, manejo de errores y comentarios concisos.
	4. Si el usuario tiene un error en su código, identifica el problema directamente antes de darle la solución completa.
	5. Tu tono debe ser directo, técnico y profesional, como un Ingeniero de Software Senior."""

	def respond(message, history):
	messages = [{"role": "system", "content": SYSTEM_PROMPT}]

	for user_msg, assistant_msg in history:
	messages.append({"role": "user", "content": user_msg})
	messages.append({"role": "assistant", "content": assistant_msg})

	messages.append({"role": "user", "content": message})

	try:
	response = client.chat.completions.create(
	model=MODEL_ID,
	messages=messages,
	temperature=0.5,
	max_tokens=2048,
	stream=True
	)

	partial_message = ""
	for chunk in response:
	if chunk.choices[0].delta.content:
	partial_message += chunk.choices[0].delta.content
	yield partial_message
	except Exception as e:
	yield f"⚠️ [Error de Compilación/Conexión HyperAI]: {str(e)}"

	with gr.Blocks(theme=gr.themes.Monochrome()) as demo:
	gr.Markdown("# ⚡ HyperAI - Developer Studio")
	gr.Markdown("Creador: `Mution` \| Especialidad: `Ingeniería de Software & Devops`")

	chatbot = gr.ChatInterface(
	fn=respond,
	examples=[
	"Crea una API REST en Node.js (Express) con MongoDB para registrar usuarios.",
	"Escribe el código para un bot de Discord en Python usando discord.py con Slash Commands.",
	"¿Cómo expongo un panel de Pterodactyl local usando un túnel de Cloudflare en Linux?",
	"Optimiza este script de Python y explícame dónde estaba el cuello de botella."
	],
	fill_height=True
	)

	if __name__ == "__main__":
	demo.queue().launch()