Instructions to use Modujo-AI/ModujoMoE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Modujo-AI/ModujoMoE with Transformers:

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

pipe = pipeline("text-generation", model="Modujo-AI/ModujoMoE")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Modujo-AI/ModujoMoE")
model = AutoModelForCausalLM.from_pretrained("Modujo-AI/ModujoMoE", device_map="auto")
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 Modujo-AI/ModujoMoE with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Modujo-AI/ModujoMoE

SGLang

How to use Modujo-AI/ModujoMoE 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 "Modujo-AI/ModujoMoE" \
    --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": "Modujo-AI/ModujoMoE",
		"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 "Modujo-AI/ModujoMoE" \
        --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": "Modujo-AI/ModujoMoE",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Modujo-AI/ModujoMoE with Docker Model Runner:
```
docker model run hf.co/Modujo-AI/ModujoMoE
```

ModujoMoE

Commit History

Add SFT, QSA, and Looped Transformer experiment roadmap

b152483
verified

Hu commited on about 20 hours ago

Use concise model-size labels in public model card

66bdf51
verified

Hu commited on about 20 hours ago

Document weight directories and correct pretrained model path

9ff40ec
verified

Hu commited on about 20 hours ago

Package Modujo-1B-A0.75B cleanly and remove superseded root weights

d7e49e3
verified

Hu commited on about 20 hours ago

Add exact parameter-size metadata for pretrain checkpoint 78900

e02f1ee
verified

Hu commited on about 20 hours ago

Upload pretrain checkpoint 78900 (1.0038B total, 0.7490B active)

7482748
verified

Hu commited on about 20 hours ago

Upload folder using huggingface_hub

a18b154
verified

Hu commited on 15 days ago

initial commit

8909fd0
verified

Hu commited on 15 days ago

Commit History

Add SFT, QSA, and Looped Transformer experiment roadmap b152483 verified

Use concise model-size labels in public model card 66bdf51 verified

Document weight directories and correct pretrained model path 9ff40ec verified

Package Modujo-1B-A0.75B cleanly and remove superseded root weights d7e49e3 verified

Add exact parameter-size metadata for pretrain checkpoint 78900 e02f1ee verified

Upload pretrain checkpoint 78900 (1.0038B total, 0.7490B active) 7482748 verified

Upload folder using huggingface_hub a18b154 verified

initial commit 8909fd0 verified

Add SFT, QSA, and Looped Transformer experiment roadmap

b152483
verified

Use concise model-size labels in public model card

66bdf51
verified

Document weight directories and correct pretrained model path

9ff40ec
verified

Package Modujo-1B-A0.75B cleanly and remove superseded root weights

d7e49e3
verified

Add exact parameter-size metadata for pretrain checkpoint 78900

e02f1ee
verified

Upload pretrain checkpoint 78900 (1.0038B total, 0.7490B active)

7482748
verified

Upload folder using huggingface_hub

a18b154
verified

initial commit

8909fd0
verified