Instructions to use jhu-clsp/ettin-decoder-400m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jhu-clsp/ettin-decoder-400m with Transformers:

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

pipe = pipeline("text-generation", model="jhu-clsp/ettin-decoder-400m")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/ettin-decoder-400m")
model = AutoModelForCausalLM.from_pretrained("jhu-clsp/ettin-decoder-400m")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jhu-clsp/ettin-decoder-400m 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-400m"
# 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-400m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/jhu-clsp/ettin-decoder-400m

SGLang

How to use jhu-clsp/ettin-decoder-400m 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-400m" \
    --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-400m",
		"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-400m" \
        --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-400m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jhu-clsp/ettin-decoder-400m with Docker Model Runner:
```
docker model run hf.co/jhu-clsp/ettin-decoder-400m
```

Update metadata and improve model card for Ettin decoder model

by nielsr HF Staff - opened Jul 18, 2025

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+160

-66

nielsr

Jul 18, 2025

This PR updates the model card for jhu-clsp/ettin-decoder-400m by:

Correcting the pipeline_tag from fill-mask to text-generation to accurately reflect its primary function as a decoder model for generative tasks.
Adding library_name: transformers to enable the "Use in Transformers" widget and ensure better discoverability.
Including datasets and more specific tags (ettin, decoder) in the metadata for enhanced search and contextual information.
Updating the "Models" badge count to reflect the expanded collection.
Adding direct links to the "Model Collection" and "Training Data" near the top for easier navigation.
Incorporating emojis into several section headings for improved readability and visual appeal.
Adding the comprehensive "Training and Evaluation" and "FAQ" sections from the GitHub repository's README to provide more detailed insights into model usage, evaluation, and common questions.
Adding an explicit "License" section at the end with a direct link to the repository's license file.

These changes collectively enhance the model card's accuracy, usability, and discoverability on the Hugging Face Hub.

Update metadata and improve model card for Ettin decoder modelcacef482

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