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

File size: 2,402 Bytes

a18b154

{
  "architectures": [
    "Qwen4ExpForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 248044,
  "dtype": "bfloat16",
  "eos_token_id": 248044,
  "hc_count": 4,
  "hc_lowrank": 192,
  "head_dim": 128,
  "heads_per_ngram": 8,
  "hidden_act": "silu",
  "hidden_size": 1536,
  "indexer_budget": 1024,
  "indexer_compress_ratio": 4,
  "indexer_head_dim": 64,
  "indexer_kv_heads": 1,
  "indexer_n_heads": 4,
  "initializer_range": 0.02,
  "layer_types": [
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "qwen_sparse_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "qwen_sparse_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "qwen_sparse_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "qwen_sparse_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "qwen_sparse_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "qwen_sparse_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "qwen_sparse_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "qwen_sparse_attention"
  ],
  "linear_conv_kernel_dim": 4,
  "linear_key_head_dim": 128,
  "linear_num_key_heads": 8,
  "linear_num_value_heads": 24,
  "linear_value_head_dim": 128,
  "make_ngram_vocab_size_divisible_by": 128,
  "max_position_embeddings": 32768,
  "model_type": "qwen4_exp_text",
  "moe_intermediate_size": 768,
  "ngram_size": 3,
  "ngram_vocab_size_base": 144128,
  "norm_topk_prob": true,
  "num_attention_heads": 12,
  "num_experts": 64,
  "num_experts_per_tok": 2,
  "num_hidden_layers": 32,
  "num_key_value_heads": 2,
  "number_of_conv_states": 3,
  "output_gate_type": "sigmoid",
  "output_router_logits": false,
  "pad_token_id": 248044,
  "ple_conv_kernel_size": 4,
  "ple_embed_dim": 1536,
  "ple_layer_ids": [
    2
  ],
  "rms_norm_eps": 1e-06,
  "rope_parameters": {
    "partial_rotary_factor": 0.25,
    "rope_theta": 10000000,
    "rope_type": "default"
  },
  "router_aux_loss_coef": 0.001,
  "seed": 1234,
  "shared_expert_intermediate_size": 768,
  "split_ngram_parts": 128,
  "tie_word_embeddings": false,
  "transformers_version": "5.17.0",
  "use_cache": true,
  "vocab_size": 248320
}