Instructions to use Menlo/Lucy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Menlo/Lucy with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Menlo/Lucy")
model = AutoModelForMultimodalLM.from_pretrained("Menlo/Lucy")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Menlo/Lucy with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Menlo/Lucy

SGLang

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

Docker Model Runner
How to use Menlo/Lucy with Docker Model Runner:
```
docker model run hf.co/Menlo/Lucy
```

jan-hq commited on Jul 18, 2025

Commit

24ce0ae

verified ·

1 Parent(s): a622294

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -25,7 +25,7 @@ library_name: transformers
 ## Overview
-Lucy is a compact but capable 1.7B model focused on agentic web search and lightweight browsing. Built on Qwen3-1.7B, Lucy inherits deep research capabilities from larger models while being optimized to run efficiently on mobile devices, even with CPU-only configurations.
 We achieved this through machine-generated task vectors that optimize thinking processes, smooth reward functions across multiple categories, and pure reinforcement learning without any supervised fine-tuning.
@@ -37,6 +37,7 @@ We achieved this through machine-generated task vectors that optimize thinking p
 - **🎯 Focused Reasoning**: Machine-generated task vectors optimize thinking processes for search tasks
 ## Evaluation
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65713d70f56f9538679e5a56/lG2FqLCWXq1N8lh7wlJgW.png)

 ## Overview
+Lucy is a compact but capable 1.7B model focused on agentic web search and lightweight browsing. Built on [Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B), Lucy inherits deep research capabilities from larger models while being optimized to run efficiently on mobile devices, even with CPU-only configurations.
 We achieved this through machine-generated task vectors that optimize thinking processes, smooth reward functions across multiple categories, and pure reinforcement learning without any supervised fine-tuning.
 - **🎯 Focused Reasoning**: Machine-generated task vectors optimize thinking processes for search tasks
 ## Evaluation
+Following the same MCP benchmark methodology used for [Jan-Nano](https://huggingface.co/Menlo/Jan-nano) and [Jan-Nano-128k](https://huggingface.co/Menlo/Jan-nano-128k), Lucy demonstrates impressive performance despite being only a 1.7B model, achieving higher accuracy than DeepSeek-v3 on MCP tasks.
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65713d70f56f9538679e5a56/lG2FqLCWXq1N8lh7wlJgW.png)