Instructions to use NLPclass/mt5-title-generation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NLPclass/mt5-title-generation with Transformers:

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

pipe = pipeline("text-generation", model="NLPclass/mt5-title-generation")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("NLPclass/mt5-title-generation")
model = AutoModelForSeq2SeqLM.from_pretrained("NLPclass/mt5-title-generation")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use NLPclass/mt5-title-generation with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/NLPclass/mt5-title-generation

SGLang

How to use NLPclass/mt5-title-generation 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 "NLPclass/mt5-title-generation" \
    --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": "NLPclass/mt5-title-generation",
		"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 "NLPclass/mt5-title-generation" \
        --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": "NLPclass/mt5-title-generation",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use NLPclass/mt5-title-generation with Docker Model Runner:
```
docker model run hf.co/NLPclass/mt5-title-generation
```

Ashkoofaraz commited on Nov 4, 2024

Commit

d0c86df

verified ·

1 Parent(s): 426b55d

Update README.md

Browse files

Change to text-generation text2text-generation for run pipeline correctly.

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -72,7 +72,7 @@ print(generated_title)
 # Create a text generation pipeline
-title_generation_pipeline = pipeline("text-generation", model="NLPclass/mt5-title-generation")
 generated_title = title_generation_pipeline(input_text, max_length=50, num_beams=5, early_stopping=True)
 print(generated_title)

 # Create a text generation pipeline
+title_generation_pipeline = pipeline("text2text-generation", model="NLPclass/mt5-title-generation")
 generated_title = title_generation_pipeline(input_text, max_length=50, num_beams=5, early_stopping=True)
 print(generated_title)