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)

# pip install -U transformers accelerate
# 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=256)
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
```

Hu commited on 14 days ago

Commit

66bdf51

verified ·

1 Parent(s): 9ff40ec

Use concise model-size labels in public model card

Browse files

Present the model as 1B-A0.75B and keep exact counts only in machine-readable metadata.

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -18,7 +18,7 @@ longer contains model weights and must not be loaded directly.
 | Path | Model | Meaning | Status |
 | --- | --- | --- | --- |
-| [`pretrain/Modujo-1B-A0.75B/`](./pretrain/Modujo-1B-A0.75B) | Modujo-1B-A0.75B | Continued-pretraining base model: 1.0038B total parameters and about 0.7490B active parameters per token | Available |
 | Repository root | Historical 9B-A1B architecture metadata and shared tokenizer files | The original random-initialized 9B weight shards were removed; this is not a loadable model directory | No weights |
 There are currently no SFT, chat, RL, or looped-model weights in this
@@ -30,8 +30,8 @@ their training stage and actual parameter size remain explicit.
 `pretrain/Modujo-1B-A0.75B/` is the released pretraining artifact.
 - Architecture: `Qwen4ExpForCausalLM`
-- Parameters: 1,003,821,539 total (1.0038B)
-- Active parameters per token: approximately 749,017,571 (0.7490B)
 - 36 layers with 8 routed experts per layer, top-2 routing, and one shared expert
 - Attention layout: repeating 3 Gated DeltaNet layers + 1 dense-attention layer
 - Context configuration: 32K maximum positions; training sequences were up to 2,048 tokens
@@ -40,7 +40,7 @@ their training stage and actual parameter size remain explicit.
 - Not instruction-tuned and not intended to be treated as a chat model
 - No QSA sparse indexer in this release
-Exact size metadata is recorded in
 [`parameter_summary.json`](./pretrain/Modujo-1B-A0.75B/parameter_summary.json).
 ## Loading

 | Path | Model | Meaning | Status |
 | --- | --- | --- | --- |
+| [`pretrain/Modujo-1B-A0.75B/`](./pretrain/Modujo-1B-A0.75B) | Modujo-1B-A0.75B | Continued-pretraining base model: 1B total scale and A0.75B active scale | Available |
 | Repository root | Historical 9B-A1B architecture metadata and shared tokenizer files | The original random-initialized 9B weight shards were removed; this is not a loadable model directory | No weights |
 There are currently no SFT, chat, RL, or looped-model weights in this
 `pretrain/Modujo-1B-A0.75B/` is the released pretraining artifact.
 - Architecture: `Qwen4ExpForCausalLM`
+- Model size: 1B total scale
+- Active size: approximately A0.75B per token
 - 36 layers with 8 routed experts per layer, top-2 routing, and one shared expert
 - Attention layout: repeating 3 Gated DeltaNet layers + 1 dense-attention layer
 - Context configuration: 32K maximum positions; training sequences were up to 2,048 tokens
 - Not instruction-tuned and not intended to be treated as a chat model
 - No QSA sparse indexer in this release
+Detailed machine-readable size metadata is recorded in
 [`parameter_summary.json`](./pretrain/Modujo-1B-A0.75B/parameter_summary.json).
 ## Loading