Instructions to use McGill-NLP/flan-t5-base-weblinx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use McGill-NLP/flan-t5-base-weblinx with Transformers:

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

pipe = pipeline("text-generation", model="McGill-NLP/flan-t5-base-weblinx")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("McGill-NLP/flan-t5-base-weblinx", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use McGill-NLP/flan-t5-base-weblinx with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "McGill-NLP/flan-t5-base-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/flan-t5-base-weblinx",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/McGill-NLP/flan-t5-base-weblinx

SGLang

How to use McGill-NLP/flan-t5-base-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/flan-t5-base-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/flan-t5-base-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/flan-t5-base-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/flan-t5-base-weblinx",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use McGill-NLP/flan-t5-base-weblinx with Docker Model Runner:
```
docker model run hf.co/McGill-NLP/flan-t5-base-weblinx
```

McGill-NLP
/

flan-t5-base-weblinx

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b63653af15c5fcbf1fc58efe47f897f1575fb2f433b94b4cbf924e1502cf18e3
+size 1558

+version https://git-lfs.github.com/spec/v1
+oid sha256:8e1f5fe6985d189e6afadfc6aa83d9ff25d57e7637490f614fffb35f4076d1c3
+size 142

+version https://git-lfs.github.com/spec/v1
+oid sha256:83e63cfe9a01be5fc4e5dcc6a6736a934e452950665253875e1c8bf019e177ba
+size 118708057

+version https://git-lfs.github.com/spec/v1
+oid sha256:686200e4b2dc4f94a11a21d00d80c58977a221bafdcad6f6f7939211a4e3de05
+size 495189552

+version https://git-lfs.github.com/spec/v1
+oid sha256:5c87151ef0f72a99d1f766a4c418bd2a1f90aaa30a8e22fe5eca9641daebb64f
+size 2201

+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

+version https://git-lfs.github.com/spec/v1
+oid sha256:6e1cae6a6e7c807a4bc6079069e8c3ef744e0ee29d573c2660717a1f6dedacba
+size 2422291

+version https://git-lfs.github.com/spec/v1
+oid sha256:6fa625547e73f7a565e5fa7f6cc0b89e61c521c15816c8415238f639fa5b9e21
+size 20771

+version https://git-lfs.github.com/spec/v1
+oid sha256:16fefc908440907c606354de838ea9361c4ef05e8dd69c819e37c68afc403d40
+size 1369

+version https://git-lfs.github.com/spec/v1
+oid sha256:fd2bfe2d7c810ab64945f68adc7043d750c34e2370d7f3657afde4f2fe8231ab
+size 4411

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@