Instructions to use obss/mt5-base-3task-highlight-combined3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use obss/mt5-base-3task-highlight-combined3 with Transformers:

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

pipe = pipeline("text-generation", model="obss/mt5-base-3task-highlight-combined3")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("obss/mt5-base-3task-highlight-combined3")
model = AutoModelForSeq2SeqLM.from_pretrained("obss/mt5-base-3task-highlight-combined3")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use obss/mt5-base-3task-highlight-combined3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "obss/mt5-base-3task-highlight-combined3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "obss/mt5-base-3task-highlight-combined3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/obss/mt5-base-3task-highlight-combined3

SGLang

How to use obss/mt5-base-3task-highlight-combined3 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 "obss/mt5-base-3task-highlight-combined3" \
    --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": "obss/mt5-base-3task-highlight-combined3",
		"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 "obss/mt5-base-3task-highlight-combined3" \
        --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": "obss/mt5-base-3task-highlight-combined3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use obss/mt5-base-3task-highlight-combined3 with Docker Model Runner:
```
docker model run hf.co/obss/mt5-base-3task-highlight-combined3
```

mt5-base-3task-highlight-combined3

Commit History

update citation

5ee3af7

fcakyon commited on Dec 14, 2022

Update README.md

3a56e22

Fatih commited on Dec 3, 2021

Update README.md

92fe115

Fatih commited on Dec 3, 2021

Update README.md

06eeb7f

Fatih commited on Dec 3, 2021

update trained data on readme

08aaeb0

fcakyon commited on Dec 3, 2021

initial commit

a80d4fd

fcakyon commited on Dec 3, 2021

initial commit

cd4f2dc

system HF Staff commited on Dec 3, 2021

Commit History

update citation 5ee3af7

Update README.md 3a56e22

Update README.md 92fe115

Update README.md 06eeb7f

update trained data on readme 08aaeb0

initial commit a80d4fd

initial commit cd4f2dc

update citation

5ee3af7

Update README.md

3a56e22

Update README.md

92fe115

Update README.md

06eeb7f

update trained data on readme

08aaeb0

initial commit

a80d4fd

initial commit

cd4f2dc