Instructions to use wnma3mz/Janus-Pro-1B-LM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wnma3mz/Janus-Pro-1B-LM with Transformers:

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

pipe = pipeline("text-generation", model="wnma3mz/Janus-Pro-1B-LM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("wnma3mz/Janus-Pro-1B-LM")
model = AutoModelForCausalLM.from_pretrained("wnma3mz/Janus-Pro-1B-LM", 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 wnma3mz/Janus-Pro-1B-LM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wnma3mz/Janus-Pro-1B-LM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wnma3mz/Janus-Pro-1B-LM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/wnma3mz/Janus-Pro-1B-LM

SGLang

How to use wnma3mz/Janus-Pro-1B-LM 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 "wnma3mz/Janus-Pro-1B-LM" \
    --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": "wnma3mz/Janus-Pro-1B-LM",
		"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 "wnma3mz/Janus-Pro-1B-LM" \
        --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": "wnma3mz/Janus-Pro-1B-LM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use wnma3mz/Janus-Pro-1B-LM with Docker Model Runner:
```
docker model run hf.co/wnma3mz/Janus-Pro-1B-LM
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

This model is derived from https://huggingface.co/deepseek-ai/Janus-Pro-1B and the main modifications are as follows

bin files are updated to safetensors
Add chat_template

4bit refers to quantifying the LLM part to 4 bits.

LM means that it contains only the language model part.

Quick Start

In Macos (Apple silicon), use mlx framework https://github.com/wnma3mz/tLLM

tllm.server --model_path $MODEL_PATH --hostname localhost --is_local --client_size 1

$MODEL_PATH like wnma3mz/Janus-Pro-1B-4bit

Downloads last month: 11

Safetensors

Model size

2B params

Tensor type

F16

Model tree for wnma3mz/Janus-Pro-1B-LM

Base model

deepseek-ai/Janus-Pro-1B

Finetuned

(6)

this model

Quantizations

2 models

Collection including wnma3mz/Janus-Pro-1B-LM

mlx-Janus-Pro

Collection

8 items • Updated Jan 30, 2025 • 3