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

Libraries

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

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

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

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Use Docker

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

SGLang

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

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

xhluca commited on Feb 10, 2024

Commit

e4dfe9e

verified ·

1 Parent(s): f108658

Create README.md

Browse files

Files changed (1) hide show

README.md +38 -0

README.md ADDED Viewed

	@@ -0,0 +1,38 @@

+---
+datasets:
+- McGill-NLP/WebLINX
+- McGill-NLP/WebLINX-full
+language:
+- en
+metrics:
+- f1
+- iou
+- chrf
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- weblinx
+- text-generation-inference
+- web-agents
+- agents
+license: apache-2.0
+---
+<div align="center">
+  <h1 style="margin-bottom: 0.5em;">WebLINX: Real-World Website Navigation with Multi-Turn Dialogue</h1>
+  <em>Xing Han Lù*, Zdeněk Kasner*, Siva Reddy</em>
+</div>
+<div style="margin-bottom: 2em"></div>
+<div style="display: flex; justify-content: space-around; align-items: center; font-size: 120%;">
+  <div><a href="https://mcgill-nlp.github.io/weblinx">🌐Website</a></div>
+  <div><a href="https://huggingface.co/spaces/McGill-NLP/weblinx-explorer">💻Explorer</a></div>
+  <div><a href="https://huggingface.co/datasets/McGill-NLP/WebLINX">🤗Dataset</a></div>
+  <div><a href="https://github.com/McGill-NLP/weblinx">💾Code</a></div>
+</div>
+## Original Model
+This model is finetuned on WebLINX using checkpoints previously published on Huggingface Hub.\
+[Click here to access the original model.](https://huggingface.co/osunlp/MindAct_ActionPrediction_flan-t5-large)