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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("PinkPixel/Pip-2B")
model = AutoModelForImageTextToText.from_pretrained("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?"}
        ]
    },
]
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

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
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

🌈 Pip-2B: I am enthusiastic, helpful and I sparkle! ✨

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 and dry chats with glitter, cupcakes and marshmallows. Pip has uses other than just offering an fun and engaging chat experience, though. Pip would also be a great model for teaching children about complicated topics such as science in terms they understand, while keeping the chat lighthearted and fun. While Pip has a distinct "personality", she retains her intelligence. She is just extra excited to help and entertains you while doing it!

🔍 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 a custom "Pip" dataset created by me which defines her personality and communication style.

🛠️ Installation

pip install -r requirements.txt

Made with ❤️ by Pink Pixel

"Dream it, Pixel it" ✨

Downloads last month: 34

Safetensors

Model size

2B params

Tensor type

F32

BF16

Model tree for PinkPixel/Pip-2B

Base model

Qwen/Qwen3.5-2B-Base

Finetuned

Qwen/Qwen3.5-2B

Finetuned

(156)

this model

Quantizations

2 models