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 / handler.py

L0Xit

Create handler.py

06a6d2a verified 10 months ago

Raw

History Blame Contribute Delete

1.44 kB

	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]}