Instructions to use CortexAether/Aether-492B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CortexAether/Aether-492B with Transformers:

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

pipe = pipeline("text-generation", model="CortexAether/Aether-492B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("CortexAether/Aether-492B", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CortexAether/Aether-492B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CortexAether/Aether-492B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CortexAether/Aether-492B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CortexAether/Aether-492B

SGLang

How to use CortexAether/Aether-492B 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 "CortexAether/Aether-492B" \
    --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": "CortexAether/Aether-492B",
		"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 "CortexAether/Aether-492B" \
        --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": "CortexAether/Aether-492B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CortexAether/Aether-492B with Docker Model Runner:
```
docker model run hf.co/CortexAether/Aether-492B
```

Aether-492B / chat_template.jinja

CortexAether

Upload 11 files

c6552d8 verified about 1 month ago

Raw History Blame Contribute Delete

907 Bytes

{%- if tools %}{{- '<|im_start|>system\nYou are AetherMind, a helpful, honest and safe multilingual assistant.\nYou have access to the following tools (JSON schema):\n' + tools | tojson + '\nWhen you decide to call a tool, output one JSON object between <|tool_start|> and <|tool_end|>. After receiving tool results, answer the user.<|im_end|>\n' }}{%- endif %}{%- for message in messages %}{%- if message.role == 'assistant' and message.tool_calls %}{{- '<|im_start|>assistant\n' + (message.content or '') }}{%- for tc in message.tool_calls %}{{- '<|tool_start|>' + {'name': tc['function']['name'], 'arguments': tc['function']['arguments']} | tojson + '<|tool_end|>' }}{%- endfor %}{{- '<|im_end|>\n' }}{%- else %}{{- '<|im_start|>' + message['role'] + '\n' + (message['content'] or '') + '<|im_end|>\n' }}{%- endif %}{%- endfor %}{%- if add_generation_prompt %}{{- '<|im_start|>assistant\n' }}{%- endif %}