Instructions to use martinsinnona/visdecode_2024_plotqa_20k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use martinsinnona/visdecode_2024_plotqa_20k with Transformers:

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

pipe = pipeline("image-text-to-text", model="martinsinnona/visdecode_2024_plotqa_20k")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("martinsinnona/visdecode_2024_plotqa_20k")
model = AutoModelForMultimodalLM.from_pretrained("martinsinnona/visdecode_2024_plotqa_20k", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use martinsinnona/visdecode_2024_plotqa_20k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "martinsinnona/visdecode_2024_plotqa_20k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "martinsinnona/visdecode_2024_plotqa_20k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/martinsinnona/visdecode_2024_plotqa_20k

SGLang

How to use martinsinnona/visdecode_2024_plotqa_20k 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 "martinsinnona/visdecode_2024_plotqa_20k" \
    --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": "martinsinnona/visdecode_2024_plotqa_20k",
		"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 "martinsinnona/visdecode_2024_plotqa_20k" \
        --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": "martinsinnona/visdecode_2024_plotqa_20k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use martinsinnona/visdecode_2024_plotqa_20k with Docker Model Runner:
```
docker model run hf.co/martinsinnona/visdecode_2024_plotqa_20k
```

martinsinnona commited on May 15, 2024

Commit

e87f39a

verified ·

1 Parent(s): b297fae

Upload Pix2StructForConditionalGeneration

Browse files

Files changed (1) hide show

model.safetensors +1 -1

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9aed2e6a605fc7bb54e1b03203916eebf48b17efd2813eda8cf5a1a9e1eb3598
 size 1129177976

 version https://git-lfs.github.com/spec/v1
+oid sha256:1107edac9f2288823dd12d0feea5e5bb04aaaec3a349cf6c8b5dac175e6ecba9
 size 1129177976