Instructions to use xjtupanda/HawkVL-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xjtupanda/HawkVL-2B with Transformers:

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

pipe = pipeline("image-text-to-text", model="xjtupanda/HawkVL-2B")
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 AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("xjtupanda/HawkVL-2B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use xjtupanda/HawkVL-2B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xjtupanda/HawkVL-2B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xjtupanda/HawkVL-2B",
		"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/xjtupanda/HawkVL-2B

SGLang

How to use xjtupanda/HawkVL-2B 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 "xjtupanda/HawkVL-2B" \
    --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": "xjtupanda/HawkVL-2B",
		"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 "xjtupanda/HawkVL-2B" \
        --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": "xjtupanda/HawkVL-2B",
		"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 xjtupanda/HawkVL-2B with Docker Model Runner:
```
docker model run hf.co/xjtupanda/HawkVL-2B
```

HawkVL-2B / README.md

xjtupanda

Update README.md

9f71276 verified about 1 year ago

preview code

Raw

History Blame Contribute Delete

1.26 kB

metadata

license: apache-2.0
datasets:
  - lmms-lab/LLaVA-OneVision-Data
language:
  - en
  - zh
base_model:
  - Qwen/Qwen2.5-1.5B-Instruct
pipeline_tag: image-text-to-text
library_name: transformers

Introduction

We are excited to introduce HawkVL, a series of multimodal large language models (MLLMs) featuring light-weight and efficiency.

Architecture:

ViT: Qwen-ViT
Projector: 2-layer MLP with pixel unshuffle
LLM: Qwen2.5-1.5B

Evaluation

We evaluate on eight benchmarks specified in the OpenCompass leaderboard using VLMEvalKit, including:

MMBench_TEST_EN/CN_V11, MMStar, MMMU_DEV_VAL, MathVista_MINI, HallusionBench, AI2D_TEST, OCRBench, MMVet

The results are as follows:

Benchmark	HawkVL-2B
MMBench-TEST-avg	64.9
MMStar	48.2
MMMU-VAL	43.9
MathVista_MINI	44.1
HallusionBench	58.5
AI2D_TEST	67.4
OCRBench	74.9
MMVet	36.6
Avg	54.8

License Agreement

All of our open-source models are licensed under the Apache-2.0 license.