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

Libraries

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

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

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

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

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aethercompute/aether0-50m"
# 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",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

How to use aethercompute/aether0-50m 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" \
    --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",
		"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" \
        --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",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

AtAndDev commited on Aug 4

Commit

b83fcb5

verified ·

1 Parent(s): f716b4e

step 84

Browse files

Files changed (2) hide show

aether_checkpoint.json +6 -0
model.safetensors +1 -1

aether_checkpoint.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "run_id": "aether0-50m",
+  "epoch": 0,
+  "step": 84,
+  "trainable_manifest_digest": "40300946cfe342c20c203ddb00e7d3ac411b3b7d52df08017e578c51e0b8a1ee"
+}

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f17ab7969a789cff9edf044fce0c94f102b9ded207442056032d2ffd10f918f7
 size 100135216

 version https://git-lfs.github.com/spec/v1
+oid sha256:e86c0fcacb09e8afa6dc436bc912ada75b5754408eb5190459a1e81c246c0a47
 size 100135216