Instructions to use LGAI-EXAONE/EXAONE-Deep-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LGAI-EXAONE/EXAONE-Deep-32B with Transformers:

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

pipe = pipeline("text-generation", model="LGAI-EXAONE/EXAONE-Deep-32B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("LGAI-EXAONE/EXAONE-Deep-32B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use LGAI-EXAONE/EXAONE-Deep-32B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LGAI-EXAONE/EXAONE-Deep-32B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LGAI-EXAONE/EXAONE-Deep-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LGAI-EXAONE/EXAONE-Deep-32B

SGLang

How to use LGAI-EXAONE/EXAONE-Deep-32B 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 "LGAI-EXAONE/EXAONE-Deep-32B" \
    --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": "LGAI-EXAONE/EXAONE-Deep-32B",
		"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 "LGAI-EXAONE/EXAONE-Deep-32B" \
        --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": "LGAI-EXAONE/EXAONE-Deep-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LGAI-EXAONE/EXAONE-Deep-32B with Docker Model Runner:
```
docker model run hf.co/LGAI-EXAONE/EXAONE-Deep-32B
```

Add links to paper and Github repository

by nielsr HF Staff - opened Mar 18, 2025

base: refs/heads/main

←

from: refs/pr/3

Discussion Files changed

+14

-9

nielsr

Mar 18, 2025

This PR adds links to the paper page and Github repository, making it easier for others to find those links.

Add links to paper and Github repositoryd3de6e6c

nuxlear

LG AI Research org Mar 19, 2025

Hello, @nielsr ! Thank you for your contribution.

After reviewing your PR, we couldn't identify the differences you described in your summary. Instead, we noticed some lines were replaced and markdown code blocks were introduced, which unexpectedly broke other content.
Could you please clarify the main differences between your PR and the original content, and explain the reasoning behind these changes?

nielsr

Mar 21, 2025

Thanks for reviewing, it looks like the link to the paper page and GitHub repo are already present, therefore I close this one!

nielsr changed pull request status to closed Mar 21, 2025

nuxlear

LG AI Research org Mar 22, 2025

Thank you for your interest and contribution, @nielsr !

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