Instructions to use Dexy2/Piko-9b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Dexy2/Piko-9b with Transformers:

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

pipe = pipeline("image-text-to-text", model="Dexy2/Piko-9b")
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("Dexy2/Piko-9b")
model = AutoModelForMultimodalLM.from_pretrained("Dexy2/Piko-9b", 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 Dexy2/Piko-9b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Dexy2/Piko-9b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Dexy2/Piko-9b",
		"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/Dexy2/Piko-9b

SGLang

How to use Dexy2/Piko-9b 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 "Dexy2/Piko-9b" \
    --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": "Dexy2/Piko-9b",
		"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 "Dexy2/Piko-9b" \
        --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": "Dexy2/Piko-9b",
		"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 Dexy2/Piko-9b with Docker Model Runner:
```
docker model run hf.co/Dexy2/Piko-9b
```

Piko-9b / evaluation /custom_suite /cases /document_understanding.jsonl

Dexy2

Rewrite model card around verified evidence; correct misattributed benchmarks and config path leak

0810902 verified 5 days ago

Raw

History Blame Contribute Delete

1.85 kB

	{"id": "doc-01", "image": "receipt.png", "prompt": "Return only JSON with keys merchant, date, total.", "check": {"type": "json_keys", "value": ["merchant", "date", "total"]}}
	{"id": "doc-02", "image": "receipt.png", "prompt": "What is the VAT amount, and what percentage was applied? Answer in one sentence.", "check": {"type": "contains_all", "value": ["4.55", "20"]}}
	{"id": "doc-03", "image": "receipt.png", "prompt": "Does subtotal plus VAT equal the printed total? Answer yes or no, then give the arithmetic.", "check": {"type": "contains", "value": "yes", "casefold": true}}
	{"id": "doc-04", "image": "invoice.png", "prompt": "How many days are there between the issue date and the due date? Number only.", "check": {"type": "contains_number", "value": 30}}
	{"id": "doc-05", "image": "invoice.png", "prompt": "Which single line item contributes the most to the total? Item name only.", "check": {"type": "contains", "value": "linen", "casefold": true}}
	{"id": "doc-06", "image": "invoice.png", "prompt": "What is the unit price of the linen board? Number only.", "check": {"type": "contains", "value": "1.7"}}
	{"id": "doc-07", "image": "form.png", "prompt": "For how many days is the equipment loaned? Number only.", "check": {"type": "contains_number", "value": 14}}
	{"id": "doc-08", "image": "form.png", "prompt": "Return only JSON with keys name, department, asset_tag, due_back.", "check": {"type": "json_keys", "value": ["name", "department", "asset_tag", "due_back"]}}
	{"id": "doc-09", "image": "noisy_scan.png", "prompt": "List every line item with its corrected price, as CSV with header name,price.", "check": {"type": "contains_all", "value": ["3.15", "5.40"]}}
	{"id": "doc-10", "image": "noisy_scan.png", "prompt": "What are the last four digits of the card used? Digits only.", "check": {"type": "contains", "value": "4119"}}