Instructions to use HuggingFaceM4/VLM_WebSight_finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingFaceM4/VLM_WebSight_finetuned with Transformers:

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

pipe = pipeline("text-generation", model="HuggingFaceM4/VLM_WebSight_finetuned", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("HuggingFaceM4/VLM_WebSight_finetuned", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HuggingFaceM4/VLM_WebSight_finetuned with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceM4/VLM_WebSight_finetuned"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceM4/VLM_WebSight_finetuned",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/HuggingFaceM4/VLM_WebSight_finetuned

SGLang

How to use HuggingFaceM4/VLM_WebSight_finetuned 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 "HuggingFaceM4/VLM_WebSight_finetuned" \
    --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": "HuggingFaceM4/VLM_WebSight_finetuned",
		"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 "HuggingFaceM4/VLM_WebSight_finetuned" \
        --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": "HuggingFaceM4/VLM_WebSight_finetuned",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use HuggingFaceM4/VLM_WebSight_finetuned with Docker Model Runner:
```
docker model run hf.co/HuggingFaceM4/VLM_WebSight_finetuned
```

Reason for using PerceiverResampler/Cross-Attention/IDEFICS related modality layers?

by besiktas - opened Jan 25, 2024

Discussion

besiktas

Jan 25, 2024

I was wondering why it seems you are using a few ideas/layers from the IDEFICS model like PerceiverResampler over just linear projection/modality_projection before the input_merging? Have you all found it improves results/training or is it mostly just sticking to what IDEFICS had?

Also as it seems like the vision model being used (SiglipVisionModel) is not pretrained, is there a reason for that?

VictorSanh

Jan 25, 2024

•

edited Jan 25, 2024

that's a great question!

the vision model (extracted from siglip) is pretrained, we are not starting from sratch.

as to the resampler, we found no to very minimal loss by pooling the vision hidden states into a short sequence that is then fed to the language model. the modality projection is mainly here to transform the image hidden size to the text hidden size for each of the positions

atb29

Jan 30, 2024

It would be great if it could take into account also images in the website screenshot and all the small details in it

VictorSanh

Jan 30, 2024

It would be great if it could take into account also images in the website screenshot

yes that's part of WebSight v0.2 we are working on!

VictorSanh changed discussion status to closed Jan 30, 2024

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment