Instructions to use GSAI-ML/iLLaDA-8B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GSAI-ML/iLLaDA-8B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="GSAI-ML/iLLaDA-8B-Instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("GSAI-ML/iLLaDA-8B-Instruct", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use GSAI-ML/iLLaDA-8B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GSAI-ML/iLLaDA-8B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GSAI-ML/iLLaDA-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/GSAI-ML/iLLaDA-8B-Instruct

SGLang

How to use GSAI-ML/iLLaDA-8B-Instruct 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 "GSAI-ML/iLLaDA-8B-Instruct" \
    --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": "GSAI-ML/iLLaDA-8B-Instruct",
		"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 "GSAI-ML/iLLaDA-8B-Instruct" \
        --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": "GSAI-ML/iLLaDA-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use GSAI-ML/iLLaDA-8B-Instruct with Docker Model Runner:
```
docker model run hf.co/GSAI-ML/iLLaDA-8B-Instruct
```

Add pipeline tag, library name, and link to paper

by nielsr HF Staff - opened 6 days ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+33

-3

nielsr

6 days ago

Hi! I'm Niels from the Hugging Face community science team.

This PR improves the model card for iLLaDA-8B-Instruct by:

Adding the pipeline_tag: text-generation so users can easily find this masked diffusion language model on the Hub.
Adding the library_name: transformers metadata since the model is compatible with Hugging Face transformers via trust_remote_code=True.
Linking the model card to its arXiv paper (Improved Large Language Diffusion Models).
Adding a quickstart usage section to help users load the model programmatically.

Please let me know if you have any questions or feedback!

Add pipeline tag, library name, and link to paperbb9794df

nieshen changed pull request status to merged 3 days ago

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