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
```

ModujoMoE / sft /Modujo-4B-A0.66B /evaluation /summary.json

Modujo-AI

Add experimental Modujo 4B A0.66B SFT weights and evaluation

c58cd49 verified 16 days ago

Raw History Blame Contribute Delete

591 Bytes

{
  "checkpoint": "short/checkpoint-36000",
  "baseline": "short/checkpoint-31000",
  "teacher_stage_started": false,
  "eval_loss": 2.37972832,
  "eval_token_acc": 0.55962285,
  "ordinary_eos": 3,
  "ordinary_total": 8,
  "code_basic_pass": 4,
  "code_basic_total": 4,
  "code_expanded_pass": 4,
  "code_expanded_total": 5,
  "thinking_closed": 1,
  "thinking_eos": 1,
  "thinking_correct": 0,
  "thinking_total": 2,
  "thinking_budget": 512,
  "comparison": "CPU rerun of four step36000 cases compared with preserved step31000 CPU outputs; original step31000 weights were rotated away."
}

	{
	"checkpoint": "short/checkpoint-36000",
	"baseline": "short/checkpoint-31000",
	"teacher_stage_started": false,
	"eval_loss": 2.37972832,
	"eval_token_acc": 0.55962285,
	"ordinary_eos": 3,
	"ordinary_total": 8,
	"code_basic_pass": 4,
	"code_basic_total": 4,
	"code_expanded_pass": 4,
	"code_expanded_total": 5,
	"thinking_closed": 1,
	"thinking_eos": 1,
	"thinking_correct": 0,
	"thinking_total": 2,
	"thinking_budget": 512,
	"comparison": "CPU rerun of four step36000 cases compared with preserved step31000 CPU outputs; original step31000 weights were rotated away."
	}