Instructions to use Kwai-Keye/Keye-VL-2.0-30B-A3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kwai-Keye/Keye-VL-2.0-30B-A3B with Transformers:

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

pipe = pipeline("image-text-to-text", model="Kwai-Keye/Keye-VL-2.0-30B-A3B", trust_remote_code=True)
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("Kwai-Keye/Keye-VL-2.0-30B-A3B", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Kwai-Keye/Keye-VL-2.0-30B-A3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kwai-Keye/Keye-VL-2.0-30B-A3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kwai-Keye/Keye-VL-2.0-30B-A3B",
		"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/Kwai-Keye/Keye-VL-2.0-30B-A3B

SGLang

How to use Kwai-Keye/Keye-VL-2.0-30B-A3B 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 "Kwai-Keye/Keye-VL-2.0-30B-A3B" \
    --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": "Kwai-Keye/Keye-VL-2.0-30B-A3B",
		"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 "Kwai-Keye/Keye-VL-2.0-30B-A3B" \
        --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": "Kwai-Keye/Keye-VL-2.0-30B-A3B",
		"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 Kwai-Keye/Keye-VL-2.0-30B-A3B with Docker Model Runner:
```
docker model run hf.co/Kwai-Keye/Keye-VL-2.0-30B-A3B
```

Kwai-Keye commited on May 26

Commit

ea1e9d2

verified ·

1 Parent(s): b5162d0

Update README.md

Browse files

Files changed (1) hide show

README.md +9 -7

README.md CHANGED Viewed

@@ -206,13 +206,15 @@ messages = [
         "content": [
             {
                 "type": "video_url",
-                "video_url": {"url": video_url},
-                "preprocess_kwargs": {
-                    "fps": fps,
-                    "min_pixels": min_token*28*28,
-                    "max_pixels": max_token*28*28,
-                    "video_total_pixels":total_video_token*28*28,
-                }
             },
             {"type": "text", "text": "Describe this video."},
         ],

         "content": [
             {
                 "type": "video_url",
+                "video_url": {
+                    "url": video_url,
+                    "preprocess_kwargs": {
+                        "fps": fps,
+                        "min_pixels": min_token*28*28,
+                        "max_pixels": max_token*28*28,
+                        "video_total_pixels":total_video_token*28*28,
+                    }
+                },
             },
             {"type": "text", "text": "Describe this video."},
         ],