Instructions to use L0Xit/KANIME-V1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use L0Xit/KANIME-V1 with Transformers:

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

pipe = pipeline("image-text-to-text", model="L0Xit/KANIME-V1")
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("L0Xit/KANIME-V1")
model = AutoModelForMultimodalLM.from_pretrained("L0Xit/KANIME-V1", 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 L0Xit/KANIME-V1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "L0Xit/KANIME-V1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "L0Xit/KANIME-V1",
		"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/L0Xit/KANIME-V1

SGLang

How to use L0Xit/KANIME-V1 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 "L0Xit/KANIME-V1" \
    --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": "L0Xit/KANIME-V1",
		"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 "L0Xit/KANIME-V1" \
        --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": "L0Xit/KANIME-V1",
		"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 L0Xit/KANIME-V1 with Docker Model Runner:
```
docker model run hf.co/L0Xit/KANIME-V1
```

KANIME-V1

File size: 1,438 Bytes

06a6d2a

from typing import Dict
from transformers import AutoProcessor, AutoModelForConditionalGeneration
from PIL import Image
import torch
import base64
import io

class EndpointHandler:
    def __init__(self, path=""):
        model_id = path if path else "Qwen/Qwen2.5-VL-7B-Instruct"
        self.processor = AutoProcessor.from_pretrained(model_id)
        self.model = AutoModelForConditionalGeneration.from_pretrained(
            model_id,
            torch_dtype=torch.bfloat16,
            device_map="auto"
        )

    def __call__(self, data: Dict[str, any]) -> Dict[str, str]:
        """
        data = {
          "inputs": {
            "text": "Describe this image",
            "image": "<base64-encoded image>"   # optional
          }
        }
        """
        inputs = {}
        if "text" in data["inputs"]:
            inputs["text"] = data["inputs"]["text"]

        if "image" in data["inputs"]:
            # Bild von Base64 in PIL umwandeln
            image_bytes = base64.b64decode(data["inputs"]["image"])
            image = Image.open(io.BytesIO(image_bytes)).convert("RGB")
            inputs["images"] = image

        proc_inputs = self.processor(**inputs, return_tensors="pt").to(self.model.device)
        output_ids = self.model.generate(**proc_inputs, max_new_tokens=200)
        result = self.processor.batch_decode(output_ids, skip_special_tokens=True)
        return {"generated_text": result[0]}