Instructions to use JurinAI/JJ-1-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JurinAI/JJ-1-2B with Transformers:

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

pipe = pipeline("image-text-to-text", model="JurinAI/JJ-1-2B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("JurinAI/JJ-1-2B")
model = AutoModelForMultimodalLM.from_pretrained("JurinAI/JJ-1-2B", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use JurinAI/JJ-1-2B with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf JurinAI/JJ-1-2B:Q8_0
# Run inference directly in the terminal:
llama cli -hf JurinAI/JJ-1-2B:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf JurinAI/JJ-1-2B:Q8_0
# Run inference directly in the terminal:
llama cli -hf JurinAI/JJ-1-2B:Q8_0

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf JurinAI/JJ-1-2B:Q8_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf JurinAI/JJ-1-2B:Q8_0

Use Docker

docker model run hf.co/JurinAI/JJ-1-2B:Q8_0

Llama new
LM Studio
Jan

vLLM

How to use JurinAI/JJ-1-2B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "JurinAI/JJ-1-2B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JurinAI/JJ-1-2B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/JurinAI/JJ-1-2B:Q8_0

SGLang

How to use JurinAI/JJ-1-2B 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 "JurinAI/JJ-1-2B" \
    --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": "JurinAI/JJ-1-2B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "JurinAI/JJ-1-2B" \
        --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": "JurinAI/JJ-1-2B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Ollama
How to use JurinAI/JJ-1-2B with Ollama:
```
ollama run hf.co/JurinAI/JJ-1-2B:Q8_0
```
Unsloth Desktop

How to use JurinAI/JJ-1-2B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf JurinAI/JJ-1-2B:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "JurinAI/JJ-1-2B:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use JurinAI/JJ-1-2B with Docker Model Runner:
```
docker model run hf.co/JurinAI/JJ-1-2B:Q8_0
```

Lemonade

How to use JurinAI/JJ-1-2B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull JurinAI/JJ-1-2B:Q8_0

Run and chat with the model

lemonade run user.JJ-1-2B-Q8_0

List all available models

lemonade list

Hermes Agent

How to use JurinAI/JJ-1-2B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf JurinAI/JJ-1-2B:Q8_0

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default JurinAI/JJ-1-2B:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use JurinAI/JJ-1-2B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf JurinAI/JJ-1-2B:Q8_0

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "JurinAI/JJ-1-2B:Q8_0" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

JJ-1-2B / example.py

LewisLuo

Add model weights and inference

dbf752e verified 20 days ago

Raw History Blame Contribute Delete

1.76 kB

"""Run the same Japanese request through Transformers or llama.cpp."""
import argparse
import json
from pathlib import Path

STATE = "洗面所の天井から水が落ち続けていて、床が水浸しです。至急見に来てください。"
QUESTIONS = {
    "category": {
        "type": "choice",
        "instructions": "問い合わせの種類は？",
        "criteria": {"water": "水漏れ", "noise": "騒音", "other": "その他"},
    },
    "needs_visit": {"type": "noul", "instructions": "現地での対応が必要ですか？"},
    "urgency": {
        "type": "score",
        "instructions": "対応の緊急度は？",
        "criteria": ["急がない", "数日以内", "今すぐ"],
    },
}


def main():
    parser = argparse.ArgumentParser(description=__doc__)
    parser.add_argument("--backend", choices=["transformers", "gguf"], default="transformers")
    parser.add_argument("--model", default=str(Path(__file__).resolve().parent))
    parser.add_argument("--device", choices=["cpu", "cuda"], default="cpu")
    parser.add_argument("--url", default="http://127.0.0.1:8081")
    args = parser.parse_args()
    if args.backend == "gguf":
        from jj1 import GGUF
        model = GGUF(args.model, url=args.url)
        try:
            answers, usage = model.decide(STATE, QUESTIONS)
        finally:
            model.close()
    else:
        import torch
        from jj1 import JJ1
        if args.device == "cpu":
            torch.set_num_threads(4)
        model = JJ1(args.model, images=False, device=args.device, max_length=4096)
        answers, usage = model.decide(STATE, QUESTIONS)
    print(json.dumps({"answers": answers, "usage": usage}, ensure_ascii=False, indent=2))


if __name__ == "__main__":
    main()

	"""Run the same Japanese request through Transformers or llama.cpp."""
	import argparse
	import json
	from pathlib import Path

	STATE = "洗面所の天井から水が落ち続けていて、床が水浸しです。至急見に来てください。"
	QUESTIONS = {
	"category": {
	"type": "choice",
	"instructions": "問い合わせの種類は？",
	"criteria": {"water": "水漏れ", "noise": "騒音", "other": "その他"},
	},
	"needs_visit": {"type": "noul", "instructions": "現地での対応が必要ですか？"},
	"urgency": {
	"type": "score",
	"instructions": "対応の緊急度は？",
	"criteria": ["急がない", "数日以内", "今すぐ"],
	},
	}


	def main():
	parser = argparse.ArgumentParser(description=__doc__)
	parser.add_argument("--backend", choices=["transformers", "gguf"], default="transformers")
	parser.add_argument("--model", default=str(Path(__file__).resolve().parent))
	parser.add_argument("--device", choices=["cpu", "cuda"], default="cpu")
	parser.add_argument("--url", default="http://127.0.0.1:8081")
	args = parser.parse_args()
	if args.backend == "gguf":
	from jj1 import GGUF
	model = GGUF(args.model, url=args.url)
	try:
	answers, usage = model.decide(STATE, QUESTIONS)
	finally:
	model.close()
	else:
	import torch
	from jj1 import JJ1
	if args.device == "cpu":
	torch.set_num_threads(4)
	model = JJ1(args.model, images=False, device=args.device, max_length=4096)
	answers, usage = model.decide(STATE, QUESTIONS)
	print(json.dumps({"answers": answers, "usage": usage}, ensure_ascii=False, indent=2))


	if __name__ == "__main__":
	main()