Instructions to use Aether-Agi/aether-v4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Aether-Agi/aether-v4 with Transformers:

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

pipe = pipeline("text-generation", model="Aether-Agi/aether-v4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Aether-Agi/aether-v4")
model = AutoModelForCausalLM.from_pretrained("Aether-Agi/aether-v4", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Aether-Agi/aether-v4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Aether-Agi/aether-v4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Aether-Agi/aether-v4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Aether-Agi/aether-v4

SGLang

How to use Aether-Agi/aether-v4 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 "Aether-Agi/aether-v4" \
    --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": "Aether-Agi/aether-v4",
		"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 "Aether-Agi/aether-v4" \
        --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": "Aether-Agi/aether-v4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Aether-Agi/aether-v4 with Docker Model Runner:
```
docker model run hf.co/Aether-Agi/aether-v4
```

aether-v4

File size: 3,367 Bytes

e4f8e05

{"exp_id": "f9d0064b", "domain": "math", "prompt": "What is 0 + 0?", "correct_response": "0", "model_response": "1", "importance": 0.8, "timestamp": 1772652747.747231, "times_replayed": 2}
{"exp_id": "4e5ee336", "domain": "math", "prompt": "What is 1 + 1?", "correct_response": "2", "model_response": "3", "importance": 0.8, "timestamp": 1772652747.747948, "times_replayed": 1}
{"exp_id": "9fa3642f", "domain": "math", "prompt": "What is 2 + 2?", "correct_response": "4", "model_response": "5", "importance": 0.8, "timestamp": 1772652747.748935, "times_replayed": 2}
{"exp_id": "3ef685a8", "domain": "math", "prompt": "What is 3 + 3?", "correct_response": "6", "model_response": "7", "importance": 0.8, "timestamp": 1772652747.749214, "times_replayed": 0}
{"exp_id": "49cf7c79", "domain": "math", "prompt": "What is 4 + 4?", "correct_response": "8", "model_response": "9", "importance": 0.8, "timestamp": 1772652747.7501812, "times_replayed": 1}
{"exp_id": "a12e5124", "domain": "math", "prompt": "What is 0 + 0?", "correct_response": "0", "model_response": "1", "importance": 0.8, "timestamp": 1772652818.0312052, "times_replayed": 0}
{"exp_id": "ec12a6f1", "domain": "math", "prompt": "What is 1 + 1?", "correct_response": "2", "model_response": "3", "importance": 0.8, "timestamp": 1772652818.0315819, "times_replayed": 0}
{"exp_id": "a16d7d4b", "domain": "math", "prompt": "What is 2 + 2?", "correct_response": "4", "model_response": "5", "importance": 0.8, "timestamp": 1772652818.032094, "times_replayed": 1}
{"exp_id": "fc5bf5f9", "domain": "math", "prompt": "What is 3 + 3?", "correct_response": "6", "model_response": "7", "importance": 0.8, "timestamp": 1772652818.032385, "times_replayed": 1}
{"exp_id": "4225bd89", "domain": "math", "prompt": "What is 4 + 4?", "correct_response": "8", "model_response": "9", "importance": 0.8, "timestamp": 1772652818.032775, "times_replayed": 0}
{"exp_id": "eac142be", "domain": "math", "prompt": "What is 0 + 0?", "correct_response": "0", "model_response": "1", "importance": 0.8, "timestamp": 1772652884.583832, "times_replayed": 0}
{"exp_id": "ac8bf06f", "domain": "math", "prompt": "What is 1 + 1?", "correct_response": "2", "model_response": "3", "importance": 0.8, "timestamp": 1772652884.5847208, "times_replayed": 0}
{"exp_id": "83b126c7", "domain": "math", "prompt": "What is 2 + 2?", "correct_response": "4", "model_response": "5", "importance": 0.8, "timestamp": 1772652884.5850308, "times_replayed": 0}
{"exp_id": "5968b591", "domain": "math", "prompt": "What is 3 + 3?", "correct_response": "6", "model_response": "7", "importance": 0.8, "timestamp": 1772652884.585928, "times_replayed": 1}
{"exp_id": "201631c7", "domain": "math", "prompt": "What is 4 + 4?", "correct_response": "8", "model_response": "9", "importance": 0.8, "timestamp": 1772652884.587326, "times_replayed": 1}
{"exp_id": "f6706834", "domain": "math", "prompt": "Q0", "correct_response": "0", "model_response": "", "importance": 0.9, "timestamp": 1772653302.982185, "times_replayed": 0}
{"exp_id": "00c5992b", "domain": "math", "prompt": "Q1", "correct_response": "1", "model_response": "", "importance": 0.9, "timestamp": 1772653302.98293, "times_replayed": 0}
{"exp_id": "5ab93549", "domain": "math", "prompt": "Q2", "correct_response": "2", "model_response": "", "importance": 0.9, "timestamp": 1772653302.983284, "times_replayed": 1}