Instructions to use sshleifer/t5-base-cnn with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sshleifer/t5-base-cnn with Transformers:

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

pipe = pipeline("text-generation", model="sshleifer/t5-base-cnn")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelWithLMHead

tokenizer = AutoTokenizer.from_pretrained("sshleifer/t5-base-cnn")
model = AutoModelWithLMHead.from_pretrained("sshleifer/t5-base-cnn", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sshleifer/t5-base-cnn with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sshleifer/t5-base-cnn"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sshleifer/t5-base-cnn",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/sshleifer/t5-base-cnn

SGLang

How to use sshleifer/t5-base-cnn 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 "sshleifer/t5-base-cnn" \
    --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": "sshleifer/t5-base-cnn",
		"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 "sshleifer/t5-base-cnn" \
        --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": "sshleifer/t5-base-cnn",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use sshleifer/t5-base-cnn with Docker Model Runner:
```
docker model run hf.co/sshleifer/t5-base-cnn
```

t5-base-cnn

Commit History

Sep 14, 2023

08:42
Adding `safetensors` variant of this model⁠

SFconvertbot

35fc181

Jun 23, 2021

14:25
allow flax

patrickvonplaten

d23d8b3

Jul 2, 2020

03:28
Update colin_preds.txt

system HF Staff

54483b1
03:28
Update colin_targets.txt

system HF Staff

908aa14

Jun 27, 2020

19:15
Update config.json

system HF Staff

e69c26d
19:15
Update pytorch_model.bin

system HF Staff

434bc21
19:15
initial commit

system HF Staff

2b9f4a9

Commit History

Sep 14, 2023

Adding `safetensors` variant of this model⁠

Jun 23, 2021

allow flax

Jul 2, 2020

Update colin_preds.txt

Update colin_targets.txt

Jun 27, 2020

Update config.json

Update pytorch_model.bin

initial commit