Instructions to use McGill-NLP/pix2act-large-weblinx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use McGill-NLP/pix2act-large-weblinx with Transformers:

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

pipe = pipeline("text-generation", model="McGill-NLP/pix2act-large-weblinx")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("McGill-NLP/pix2act-large-weblinx", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use McGill-NLP/pix2act-large-weblinx with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "McGill-NLP/pix2act-large-weblinx"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "McGill-NLP/pix2act-large-weblinx",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/McGill-NLP/pix2act-large-weblinx

SGLang

How to use McGill-NLP/pix2act-large-weblinx 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 "McGill-NLP/pix2act-large-weblinx" \
    --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": "McGill-NLP/pix2act-large-weblinx",
		"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 "McGill-NLP/pix2act-large-weblinx" \
        --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": "McGill-NLP/pix2act-large-weblinx",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use McGill-NLP/pix2act-large-weblinx with Docker Model Runner:
```
docker model run hf.co/McGill-NLP/pix2act-large-weblinx
```

pix2act-large-weblinx

Commit History

Adding `safetensors` variant of this model (#1)

d1ec516
verified

xhluca

SFconvertbot commited on Dec 12, 2024

Update README.md

e4ca33b
verified

xhluca commited on Feb 9, 2024

Create README.md

9cd8048
verified

xhluca commited on Feb 9, 2024

Add model, tokenizer, and config files, input records.

1eb63fd

xhluca commited on Feb 7, 2024

Add .json to .gitattributes to track changes in json files

9e36627

xhluca commited on Feb 7, 2024

initial commit

ff371ee
verified

xhluca commited on Feb 7, 2024

Commit History

Adding `safetensors` variant of this model (#1) d1ec516 verified

Update README.md e4ca33b verified

Create README.md 9cd8048 verified

Add model, tokenizer, and config files, input records. 1eb63fd

Add .json to .gitattributes to track changes in json files 9e36627

initial commit ff371ee verified

Adding `safetensors` variant of this model (#1)

d1ec516
verified

Update README.md

e4ca33b
verified

Create README.md

9cd8048
verified

Add model, tokenizer, and config files, input records.

1eb63fd

Add .json to .gitattributes to track changes in json files

9e36627

initial commit

ff371ee
verified