Instructions to use mkd-ai/keural-VLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mkd-ai/keural-VLM with Transformers:

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

pipe = pipeline("image-text-to-text", model="mkd-ai/keural-VLM")
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 AutoModel
model = AutoModel.from_pretrained("mkd-ai/keural-VLM", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mkd-ai/keural-VLM with vLLM:

Install from pip and serve model

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

SGLang

How to use mkd-ai/keural-VLM 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 "mkd-ai/keural-VLM" \
    --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": "mkd-ai/keural-VLM",
		"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 "mkd-ai/keural-VLM" \
        --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": "mkd-ai/keural-VLM",
		"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 mkd-ai/keural-VLM with Docker Model Runner:
```
docker model run hf.co/mkd-ai/keural-VLM
```

mkd-hika commited on Jul 2

Commit

aa35815

verified ·

1 Parent(s): a1914ad

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -5

README.md CHANGED Viewed

@@ -18,11 +18,8 @@ pipeline_tag: image-text-to-text
 #  Keural VLM — Vision-Language Model <sub>(PoC · V0.1)</sub>
-**## Overview
-Keural VLM is a proof-of-concept vision-language model developed to explore lightweight multimodal learning using a custom vision encoder. Unlike many existing VLMs, the model does not rely on a pretrained CLIP backbone. Instead, the visual encoder is trained from scratch and connected to Mistral-7B-Instruct through a lightweight projection module.
-The current release demonstrates the full training pipeline—from vision pretraining to supervised fine-tuning and Direct Preference Optimization (DPO)—while evaluating how a compact encoder performs across a range of multimodal benchmarks.**
 <p>
   <img src="https://img.shields.io/badge/MKD_Co.,_Ltd.-Keural-6d28d9?style=for-the-badge" alt="MKD">

 #  Keural VLM — Vision-Language Model <sub>(PoC · V0.1)</sub>
+**##Keural VLM is a proof-of-concept vision-language model developed to explore lightweight multimodal learning using a custom vision encoder. Unlike many existing VLMs, the model does not rely on a pretrained CLIP backbone. Instead, the visual encoder is trained from scratch and connected to Mistral-7B-Instruct through a lightweight projection module.
+.**
 <p>
   <img src="https://img.shields.io/badge/MKD_Co.,_Ltd.-Keural-6d28d9?style=for-the-badge" alt="MKD">