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

Libraries

How to use North-ML1/Aurora-Proelia-Thinking with Transformers:

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

pipe = pipeline("text-generation", model="North-ML1/Aurora-Proelia-Thinking", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("North-ML1/Aurora-Proelia-Thinking", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use North-ML1/Aurora-Proelia-Thinking with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "North-ML1/Aurora-Proelia-Thinking"
# 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/Aurora-Proelia-Thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/North-ML1/Aurora-Proelia-Thinking

SGLang

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

Docker Model Runner
How to use North-ML1/Aurora-Proelia-Thinking with Docker Model Runner:
```
docker model run hf.co/North-ML1/Aurora-Proelia-Thinking
```

Aurora-Proelia-Thinking / tokenizer_config.json

arthu1

Publish Aurora Proelia Thinking v1

0810211 verified 7 days ago

Raw

History Blame Contribute Delete

604 Bytes

	{
	"add_bos_token": true,
	"add_eos_token": false,
	"bos_token": "<bos>",
	"bos_token_id": 1,
	"chat_template": "<bos>{% for message in messages %}{% if message['role'] == 'user' %}Question: {{ message['content'] }}\nAnswer:{% elif message['role'] == 'assistant' %}{{ message['content'] }}<eos>{% endif %}{% endfor %}",
	"clean_up_tokenization_spaces": false,
	"eos_token": "<eos>",
	"eos_token_id": 2,
	"model_max_length": 2048,
	"pad_token": "<pad>",
	"pad_token_id": 0,
	"padding_side": "left",
	"tokenizer_class": "PreTrainedTokenizerFast",
	"unk_token": "<unk>",
	"unk_token_id": 3
	}