Instructions to use XenonStudio/XenonAI-0.6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use XenonStudio/XenonAI-0.6B with Transformers:

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

pipe = pipeline("text-generation", model="XenonStudio/XenonAI-0.6B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("XenonStudio/XenonAI-0.6B")
model = AutoModelForCausalLM.from_pretrained("XenonStudio/XenonAI-0.6B", 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 XenonStudio/XenonAI-0.6B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "XenonStudio/XenonAI-0.6B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "XenonStudio/XenonAI-0.6B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/XenonStudio/XenonAI-0.6B

SGLang

How to use XenonStudio/XenonAI-0.6B 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 "XenonStudio/XenonAI-0.6B" \
    --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": "XenonStudio/XenonAI-0.6B",
		"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 "XenonStudio/XenonAI-0.6B" \
        --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": "XenonStudio/XenonAI-0.6B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use XenonStudio/XenonAI-0.6B with Docker Model Runner:
```
docker model run hf.co/XenonStudio/XenonAI-0.6B
```

XenonAI-0.6B

Official Qwen3-0.6B-Base model copied to the Xenon Studio repository.

Important: This repository contains the original Qwen3-0.6B-Base model weights. It is not the fine-tuned XenonAI model.

Model Information

Model: Qwen3-0.6B-Base
Parameters: 0.6B
Layers: 28
Architecture: Causal Language Model
Original model: Qwen/Qwen3-0.6B-Base
License: Apache-2.0

Purpose

This repository is maintained by Xenon Studio as a local copy of the official Qwen3-0.6B-Base model.

The base model is used as the foundation for XenonAI model development and future fine-tuning experiments.

Attribution

The model weights and original model are provided by the Qwen Team.

Original model:

Qwen/Qwen3-0.6B-Base

Please refer to the original Qwen repository and license for the complete model documentation, usage requirements, and attribution.

XenonAI Development

Our fine-tuned XenonAI model is developed separately using this base model together with our own training data and training process.

This repository should therefore be considered the official base model copy, not the trained XenonAI release.

License

This repository retains the original Apache-2.0 licensing information associated with Qwen3-0.6B-Base.

Please review the original Qwen license before using or redistributing the model.

Original Model

For the original model documentation and technical details, please visit:

https://huggingface.co/Qwen/Qwen3-0.6B-Base

Xenon Studio

Building XenonAI.

Downloads last month: 240

Safetensors

Model size

0.8B params

Tensor type

BF16

Model tree for XenonStudio/XenonAI-0.6B

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

(699)

this model