Instructions to use aethercompute/aether0-50m-2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aethercompute/aether0-50m-2b with Transformers:

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

pipe = pipeline("text-generation", model="aethercompute/aether0-50m-2b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aethercompute/aether0-50m-2b")
model = AutoModelForCausalLM.from_pretrained("aethercompute/aether0-50m-2b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use aethercompute/aether0-50m-2b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aethercompute/aether0-50m-2b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aethercompute/aether0-50m-2b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/aethercompute/aether0-50m-2b

SGLang

How to use aethercompute/aether0-50m-2b 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 "aethercompute/aether0-50m-2b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aethercompute/aether0-50m-2b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "aethercompute/aether0-50m-2b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aethercompute/aether0-50m-2b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use aethercompute/aether0-50m-2b with Docker Model Runner:
```
docker model run hf.co/aethercompute/aether0-50m-2b
```

AETHERCOMPUTEAETHERCOMPUTEAETHERCOMPUTEAETHERCOMPUTEAETHERCOMPUTEAETHERC
E:cccclllllllloooooooooodddddddddddodddddddddddddddddddddddddddddddooooO
TcclllllllllllloooooooooddddddoooooooodddddddddddddddddddddddddddddooooM
HllllllllllllllloooooolclllllllcllccllllllllllooooddddooddddddddddoooooP
Ellllllllllllllllllccc:::clllllllc;:looooolccllllllllcloooddddddddoooooU
Rccclllllllllcc:::ccccc:;cllllccc;':llloolc:clolllc:;:lllloooooodooooooT
Ccccccccccccc:;;;:cccc:;'';:::;,'..;::::;,,;:ccc:,',:clllllllloolloooooE
Occccccccc::;;:;,'';;;;'....'.... .''''...',;,'...';ccllllllllcccclllllA
Mccccc:::;;;;;;;,........          ..     ...  ..,;::::::::::::ccllllllE
Pc::::;,,,,,,''....            ..               ........'''',:cclllccccT
U::::;,'''.................   .,,...........','...     ...',;::c:::::ccH
T::;;,,''....',;:;........     .. .........,colc:,...    .......'',,;;;E
E::;,,,'',,;:cllol:.......         ...'''',codddolc:,'...      ......',R
A:;,'',,;;:cclooool:,......... ......''',;lddxdddoolc:,'..........',;;:C
E,,',,,,;;;::ccllloll:,...............',:odddddoolcc:;,'.'''..',;;::cccO
T''',,,,,,,,,,;;::::cc:;,'....'....'',:clooolllc:;,''''''',;;;;;:clllllM
H,;;:::cc::;;;;;,,'.',,,,;;;;;,,;;;;;::::;:::;;,'...'',;::cclllllllllllP
E:::::cccccccc:;,''''...,::;,...,;,...,,'...'',,,',,;:cccllllloooooooooU
R::::::::::ccc:;,;:;'';;:lc;,..',;:,'..;:;,,;,,:ccccccloolcccllllloooooT
C::ccc:::::::::::c:;;::::llc:,';:cccc:,:llccllc:clllcccllllllllllllooooE
Occcccccccc::::::::::cc::ccc:;;::ccccc::clllcclc::cccccccllllllllooooooA
Mllllccccccccccccc::ccccccccc::::ccccc:::cccccccc::ccccccllllloooooooooE
Plllllllcccccccccccccccccccccc:cc:::::::::::::::cccccccllllooooooooooodT
UoollllllllllllllcccccclllcccccccccccccccccccccccllllllloooooooodddddddH
TEAETHERCOMPUTEAETHERCOMPUTEAETHERCOMPUTEAETHERCOMPUTEAETHERCOMPUTEAETHE

Downloads last month: 258

Safetensors

Model size

49.9M params

Tensor type

BF16