Instructions to use North-ML1/starlight-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use North-ML1/starlight-mini with Transformers:

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

pipe = pipeline("text-generation", model="North-ML1/starlight-mini")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("North-ML1/starlight-mini")
model = AutoModelForCausalLM.from_pretrained("North-ML1/starlight-mini")
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 North-ML1/starlight-mini with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "North-ML1/starlight-mini"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "North-ML1/starlight-mini",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/North-ML1/starlight-mini

SGLang

How to use North-ML1/starlight-mini 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 "North-ML1/starlight-mini" \
    --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": "North-ML1/starlight-mini",
		"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 "North-ML1/starlight-mini" \
        --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": "North-ML1/starlight-mini",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use North-ML1/starlight-mini with Docker Model Runner:
```
docker model run hf.co/North-ML1/starlight-mini
```

starlight-mini / README.md

arthu1

Update README.md

0f40fcb verified 5 months ago

preview code

Raw

History Blame Contribute Delete

1.35 kB

	---
	library_name: transformers
	tags:
	- code
	- coolness
	- north.ai
	datasets:
	- HuggingFaceH4/ultrachat_200k
	language:
	- en
	metrics:
	- accuracy
	base_model:
	- arthu1/astrocoder-star-merge
	pipeline_tag: text-generation
	---

	# Model Card for Model ID

	This model is the original model created by North.ai and fine-tuned from other models to provide 60-65% on the SWE-Benchmark. It will be helpful, but this is just our first one.


	## Model Details

	### Model Description

	<!-- Provide a longer summary of what this model is. -->

	This model is the original model created by North.ai and fine-tuned from other models to provide 60-65% on the SWE-Benchmark.
	It will be helpful, but this is just our first one.
	We are trying to find solutions to the coding shortage, for free, and Jesus Loves You! For God!

	- Developed by: arthu1 at the AI branch of Nova Devs (North.ai)
	- Model type: Conversation / Text Generation
	- Language(s) (NLP): English.
	- License: Idk, but you can host it, please don't reverse engineer or hack it.

	### Model Sources [optional]
	- Use it on: https://north-ai-ten.vercel.app (when we are finished building.)

	## Uses

	Use it for your text generation needs.
	This is somewhat Claude Haiku 5 (April 2026, possible) / GPT-Nano 5.3 (Feb 2026) Level, but more similar in intelligence to Claude Haiku 3.5 or GPT-4o.