Instructions to use LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct", 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-3.5-2.4B-Instruct", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LGAI-EXAONE/EXAONE-3.5-2.4B-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": "LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct

SGLang

How to use LGAI-EXAONE/EXAONE-3.5-2.4B-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 "LGAI-EXAONE/EXAONE-3.5-2.4B-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": "LGAI-EXAONE/EXAONE-3.5-2.4B-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 "LGAI-EXAONE/EXAONE-3.5-2.4B-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": "LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct with Docker Model Runner:
```
docker model run hf.co/LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct
```

License

by mrfakename - opened Dec 9, 2024

Discussion

mrfakename

Dec 9, 2024

Hi,
Thanks for releasing EXAONE! I noticed in your blog post you mentioned that the model was open sourced. Are there any plans to switch to an open source (OSI-approved) license?
Thanks!

N8Programs

Dec 10, 2024

•

edited Dec 10, 2024

This could be especially beneficial for the smaller model - you could keep your largest model w/ a restrictive license, but just making the tiny one Apache 2.0 (or even just a more permissive commercial license) would more than pay itself back in terms of publicity and adoption. The issue w/ a lot of awesome small models (like this one) is that they get released, they have a strange license, they never get used, and then they fall by the wayside. If you look at models by smaller teams that do really well - like Olmo, Mistral, MiniCPM, Qwen (in the beginning they were a small team haha), Yi, etc. - all of these have open source licenses.

jinsik-lee

Dec 10, 2024

Thank you so much for your kind words and for your interest in EXAONE. We truly appreciate your support and feedback. Currently, we have made the models available as open-weight for research purposes only. The OSI is currently under internal review. We will certainly keep you updated if there are any changes in the future, so please stay tuned!

jinsik-lee changed discussion status to closed Dec 10, 2024

N8Programs

Dec 10, 2024

Thank you for the prompt response! Totally understand the internal review. We will stay tuned :D!

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