Instructions to use jhu-clsp/ettin-decoder-32m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jhu-clsp/ettin-decoder-32m with Transformers:

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

pipe = pipeline("text-generation", model="jhu-clsp/ettin-decoder-32m")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/ettin-decoder-32m")
model = AutoModelForCausalLM.from_pretrained("jhu-clsp/ettin-decoder-32m")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jhu-clsp/ettin-decoder-32m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jhu-clsp/ettin-decoder-32m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jhu-clsp/ettin-decoder-32m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/jhu-clsp/ettin-decoder-32m

SGLang

How to use jhu-clsp/ettin-decoder-32m 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 "jhu-clsp/ettin-decoder-32m" \
    --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": "jhu-clsp/ettin-decoder-32m",
		"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 "jhu-clsp/ettin-decoder-32m" \
        --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": "jhu-clsp/ettin-decoder-32m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jhu-clsp/ettin-decoder-32m with Docker Model Runner:
```
docker model run hf.co/jhu-clsp/ettin-decoder-32m
```

Update pipeline tag and add library name for `ettin-decoder-32m`

by nielsr HF Staff - opened Jul 18, 2025

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+45

-42

nielsr

Jul 18, 2025

This PR improves the model card for the jhu-clsp/ettin-decoder-32m model by:

Changing the pipeline_tag from fill-mask to text-generation, accurately reflecting its primary use case as a decoder-only model for generative tasks. This ensures the model appears under the correct filter on the Hugging Face Hub (https://huggingface.co/models?pipeline_tag=text-generation).
Adding library_name: transformers to the metadata, enabling the "how to use" widget and better integration with the Hugging Face ecosystem, as the model is compatible with the library.

Update pipeline tag and add library name for `ettin-decoder-32m`d7bf2c56

orionweller changed pull request status to merged Jul 18, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment