Instructions to use LGAI-EXAONE/EXAONE-4.0-1.2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LGAI-EXAONE/EXAONE-4.0-1.2B with Transformers:

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

pipe = pipeline("text-generation", model="LGAI-EXAONE/EXAONE-4.0-1.2B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LGAI-EXAONE/EXAONE-4.0-1.2B")
model = AutoModelForCausalLM.from_pretrained("LGAI-EXAONE/EXAONE-4.0-1.2B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LGAI-EXAONE/EXAONE-4.0-1.2B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LGAI-EXAONE/EXAONE-4.0-1.2B"
# 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-4.0-1.2B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LGAI-EXAONE/EXAONE-4.0-1.2B

SGLang

How to use LGAI-EXAONE/EXAONE-4.0-1.2B 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-4.0-1.2B" \
    --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-4.0-1.2B",
		"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-4.0-1.2B" \
        --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-4.0-1.2B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LGAI-EXAONE/EXAONE-4.0-1.2B with Docker Model Runner:
```
docker model run hf.co/LGAI-EXAONE/EXAONE-4.0-1.2B
```

DeepSpeed Inference V2 support for EXAONE 4.0 (merged)

by Bias92 - opened Feb 18

Discussion

Bias92

Feb 18

DeepSpeed Inference V2 support for EXAONE 4.0

Hi EXAONE team! I've added EXAONE 4.0 model support for DeepSpeed Inference V2, and it has been merged into the main branch.

PR: https://github.com/deepspeedai/DeepSpeed/pull/7853

Key implementation details:

Post-norm architecture (RMSNorm after attention/MLP)
QK-Norm (per-head RMSNorm on Q and K projections)
Hybrid sliding window / full attention support for 32B model

Both EXAONE-4.0-1.2B and EXAONE-4.0-32B are supported.

Hope this is useful for the community!

lkm2835

LG AI Research org Feb 18

Thank you for your contribution!

Bias92

Feb 18

"You're very welcome! I'm glad to be of help. I believe the DeepSpeed Inference V2 support, especially with the QK-Norm and Hybrid Sliding Window implementation, will significantly boost the serving efficiency for the EXAONE 4.0 community. Let me know if there are any further optimizations you'd like to see!"

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