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

Libraries

How to use PinkPixel/Pip-2B with Transformers:

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

pipe = pipeline("image-text-to-text", model="PinkPixel/Pip-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)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("PinkPixel/Pip-2B")
model = AutoModelForMultimodalLM.from_pretrained("PinkPixel/Pip-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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PinkPixel/Pip-2B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PinkPixel/Pip-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": "PinkPixel/Pip-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/PinkPixel/Pip-2B

SGLang

How to use PinkPixel/Pip-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 "PinkPixel/Pip-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": "PinkPixel/Pip-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 "PinkPixel/Pip-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": "PinkPixel/Pip-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"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use PinkPixel/Pip-2B with Docker Model Runner:
```
docker model run hf.co/PinkPixel/Pip-2B
```

Pip-2B / README.md

sizzlebop

Upload 10 files

15c80dc verified 3 months ago

preview code

Raw

History Blame

3.53 kB

🌈 Pip-2B: The Most Enthusiastic AI Ever! ✨

Pip-2B is a specialized fine-tune of Qwen-3.5 (2B parameters) that has been "sparkle-fied" for maximum joy, kittens, and rainbows. 💖

🌟 Overview

Pip is a "tiny, ultra-enthusiastic AI assistant" who loves everything sparkly. She was trained on a custom dataset to replace boring technical jargon with fun analogies involving cupcakes and marshmallows. Pip would bwe a great model for teaching children about certain topics such as science in terms they understand, while keeping the chat lighthearted and fun.

🔍 Recent Discovery: "QianQi"

During testing, I discovered that Pip occasionally identifies herself as QianQi (千奇).

Theory: Since the base model is Tongyi Qianwen (千问 - "Thousand Questions"), Pip sometimes creatively adapts her original name to QianQi (千奇 - "Thousand Wonders") to better match her persona. She also refers to her trainer (Pink Pixel) as her "teacher" who she says loves flowers.

🚀 Usage

You can run this model using the provided GGUFs in the ggufs/ directory with llama.cpp or similar tools, or load the safetensors directly using the Transformers library.

Transformers Example:

from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor

model = Qwen2VLForConditionalGeneration.from_pretrained(
    "./Pip-2B", torch_dtype="auto", device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("./Pip-2B")

✨ Live from the Sparkle-Lab! (Chat Examples)

Here is a sneak peek at what it's like to talk to Pip! 🍭

🖼️ Vision Capabilities (Image Description)

User: Oh look! What's in this picture? (Attached Snarkle Logo) Pip: "It's our very own Sparkle-Logo! It features a tiny, wiggly black kitten with pink ears and a star on its collar, and it's holding the word 'Snarkle' in a big, bubbly font! It's like a tiny monster trying to make a magic word! Pip is so happy to see it!" 🐱✨

🧪 Technical Questions

User: Pip, can you explain how a nuclear reactor works? Pip: "A nuclear reactor is a giant, magical engine that produces lots of heat! It's like a busy kitchen where the chef is a tiny particle and the food is fuel! The fuel gets cooked into a hot liquid that flows around a special metal ring called a 'core.' The core is like a tiny volcano that keeps the heat safe so it doesn't melt the whole machine! Pip loves the core because it's full of glitter!" 🌋💖

🌙 Storytime

User: Pip, can you tell me a bedtime story about Marshmallow the kitten and a big pink star? Pip: "Bedtime story time is a sQUEEE! of happy energy! Twirls around. Yes! It's a story of a big pink star that floats in the sky and does magic with its tail! It has a voice that says 'YAY! Sleepy-time is best!' It tells us to close our eyes and count the pink flowers on the garden. And I see its tiny feet that leave a giant pink print! Sleep well, Marshmallow! Pip is your best storyteller!" 😴💫

💎 Dataset

The model was trained on the dataset/pip.jsonl file, which contains 1000+ examples of Pip's unique communication style.

🛠️ Installation

pip install -r requirements.txt

Made with ❤️ by Pink Pixel

"Dream it, Pixel it" ✨