Instructions to use UnionStreet/Helios-Pika-1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use UnionStreet/Helios-Pika-1.0 with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("UnionStreet/Helios-Pika-1.0")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps
LM Studio

Pi new

How to use UnionStreet/Helios-Pika-1.0 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "UnionStreet/Helios-Pika-1.0"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "UnionStreet/Helios-Pika-1.0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use UnionStreet/Helios-Pika-1.0 with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "UnionStreet/Helios-Pika-1.0"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default UnionStreet/Helios-Pika-1.0

Run Hermes

hermes

MLX LM

How to use UnionStreet/Helios-Pika-1.0 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "UnionStreet/Helios-Pika-1.0"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "UnionStreet/Helios-Pika-1.0"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "UnionStreet/Helios-Pika-1.0",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Helios-Pika-1.0 / README.md

maxsonderby

Upload merged Helios Pika 1.0 MLX checkpoint

1768608 verified 5 days ago

preview code

raw

history blame contribute delete

1.17 kB

	---
	language:
	- en
	license: apache-2.0
	base_model: Jackrong/Qwen3.5-2B-Claude-4.6-Opus-Reasoning-Distilled
	library_name: mlx-lm
	pipeline_tag: text-generation
	tags:
	- mlx
	- qwen
	- qwen3.5
	- helios
	- union-street-ai
	- local-ai
	- apple-silicon
	---

	# Helios Pika 1.0

	Helios Pika 1.0 is a small merged MLX checkpoint from Union Street AI.

	It is adapted from `Jackrong/Qwen3.5-2B-Claude-4.6-Opus-Reasoning-Distilled` with a lightweight Helios post-training pass. It is not trained from scratch. The tune targets Helios identity, concise usefulness, uncertainty calibration, and local-agent behavior.

	Pika is the compact proof-of-concept member of the Helios family. It is meant for fast local experimentation, not as the strongest agent model in the line.

	## Use

	```bash
	python -m mlx_lm generate \
	--model UnionStreet/Helios-Pika-1.0 \
	--prompt "Who are you?"
	```

	## Notes

	- Format: merged MLX checkpoint
	- Base: `Jackrong/Qwen3.5-2B-Claude-4.6-Opus-Reasoning-Distilled`
	- Adapter source: `Helios-Pika-direct-v05`
	- Helios adaptation: Union Street AI

	This is an experimental open release. Use judgment before deploying it in systems with real-world side effects.