Instructions to use LucidityAI/Astral-4B-Preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LucidityAI/Astral-4B-Preview with Transformers:

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

pipe = pipeline("text-generation", model="LucidityAI/Astral-4B-Preview")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LucidityAI/Astral-4B-Preview")
model = AutoModelForCausalLM.from_pretrained("LucidityAI/Astral-4B-Preview")
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

vLLM

How to use LucidityAI/Astral-4B-Preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LucidityAI/Astral-4B-Preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LucidityAI/Astral-4B-Preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LucidityAI/Astral-4B-Preview

SGLang

How to use LucidityAI/Astral-4B-Preview 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 "LucidityAI/Astral-4B-Preview" \
    --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": "LucidityAI/Astral-4B-Preview",
		"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 "LucidityAI/Astral-4B-Preview" \
        --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": "LucidityAI/Astral-4B-Preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LucidityAI/Astral-4B-Preview with Docker Model Runner:
```
docker model run hf.co/LucidityAI/Astral-4B-Preview
```

Astral-4B-Preview / README.md

sd-inf

Update README.md

4fc0205 verified 8 months ago

preview code

raw

history blame contribute delete

1.77 kB

	---
	license: apache-2.0
	base_model: Qwen/Qwen3-4b-thinking-2507
	tags:
	- reasoning
	- code
	- inference
	- chat
	library_name: transformers
	datasets:
	- nvidia/AceReason-1.1-SFT
	new_version: LucidityAI/Astral-4B
	---

	# Astral-4B-Preview


	Astral-4B is a specialized reasoning-focused language model developed as part of the Astral series, designed to deliver high-fidelity, step-by-step reasoning with configurable depth. Built upon the Qwen3-4b-thinking-2507 foundation, this variant has been fine-tuned on the `nvidia/AceReason-1.1-SFT` dataset to enhance logical coherence, problem-solving capability, and structured thinking.

	This model is currently in preview and intended for research, evaluation, and development use. Feedback is encouraged to guide future iterations.

	---

	## Usage Instructions

	To invoke the model correctly, include a reasoning-level indicator in the system prompt using the `Reasoning-level:` directive. The available levels are:

	\| Level \| Behavior \|
	\|----------\|--------\|
	\| `none` \| No reasoning trace generated, direct response only. \|
	\| `low` \| Minimal internal reasoning \|
	\| `medium` \| Creates a reasoning trace thats not too long nor too short \|
	\| `high` \| Second highest reasoning depth \|
	\| `ultra` \| Maximum depth reasoning \|

	> Note: The absence of a valid reasoning level will result in undefined behavior. Always specify one.

	### Example Prompt (ChatML Format):

	```xml
	<\|im_start\|>system
	Reasoning-level: high
	<\|im_end\|>
	<\|im_start\|>user
	What is the capital of France?
	<\|im_end\|>
	<\|im_start\|>assistant
	<think>

	```

	---

	## Important Notes

	- This is a preview release. Performance may vary across edge cases or non-standard inputs.
	- For production applications, please wait for the official release.

	---