Instructions to use fmb-quibdo/qwen2-vl-fmb with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fmb-quibdo/qwen2-vl-fmb with Transformers:

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

pipe = pipeline("image-text-to-text", model="fmb-quibdo/qwen2-vl-fmb")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("fmb-quibdo/qwen2-vl-fmb")
model = AutoModelForMultimodalLM.from_pretrained("fmb-quibdo/qwen2-vl-fmb")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use fmb-quibdo/qwen2-vl-fmb with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fmb-quibdo/qwen2-vl-fmb"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fmb-quibdo/qwen2-vl-fmb",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/fmb-quibdo/qwen2-vl-fmb

SGLang

How to use fmb-quibdo/qwen2-vl-fmb 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 "fmb-quibdo/qwen2-vl-fmb" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fmb-quibdo/qwen2-vl-fmb",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "fmb-quibdo/qwen2-vl-fmb" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fmb-quibdo/qwen2-vl-fmb",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use fmb-quibdo/qwen2-vl-fmb with Docker Model Runner:
```
docker model run hf.co/fmb-quibdo/qwen2-vl-fmb
```

qwen2-vl-fmb / config.json

Commit History

Upload Qwen2VLForConditionalGeneration

e49c310
verified

Andy Janco commited on Sep 17, 2024

Upload Qwen2VLForConditionalGeneration

18027c1
verified

Andy Janco commited on Sep 17, 2024

Commit History

Upload Qwen2VLForConditionalGeneration e49c310 verified

Upload Qwen2VLForConditionalGeneration 18027c1 verified

Upload Qwen2VLForConditionalGeneration

e49c310
verified

Upload Qwen2VLForConditionalGeneration

18027c1
verified