Instructions to use BigSalmon/PointsToSentence with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BigSalmon/PointsToSentence with Transformers:

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

pipe = pipeline("text-generation", model="BigSalmon/PointsToSentence")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BigSalmon/PointsToSentence")
model = AutoModelForCausalLM.from_pretrained("BigSalmon/PointsToSentence")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use BigSalmon/PointsToSentence with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/BigSalmon/PointsToSentence

SGLang

How to use BigSalmon/PointsToSentence 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 "BigSalmon/PointsToSentence" \
    --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": "BigSalmon/PointsToSentence",
		"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 "BigSalmon/PointsToSentence" \
        --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": "BigSalmon/PointsToSentence",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use BigSalmon/PointsToSentence with Docker Model Runner:
```
docker model run hf.co/BigSalmon/PointsToSentence
```

PointsToSentence / README.md

BigSalmon

Update README.md

ae6ce92 about 4 years ago

preview code

raw

history blame contribute delete

981 Bytes

	```
	from transformers import AutoTokenizer, AutoModelForCausalLM

	tokenizer = AutoTokenizer.from_pretrained("BigSalmon/PointsToSentence")

	model = AutoModelForCausalLM.from_pretrained("BigSalmon/PointsToSentence")
	```

	```
	- moviepass to return
	- this summer
	- swooped up by
	- original co-founder stacy spikes
	text: the re-launch of moviepass is set to transpire this summer, ( rescued at the hands of / under the stewardship of / spearheaded by ) its founding father, stacy spikes.

	***

	- middle schools do not have recess
	- should get back to doing it
	- amazing for communication
	- and getting kids to move around
	text: a casualty of the education reform craze, recess has been excised from middle schools. this is tragic, for it is instrumental in honing children's communication skills and encouraging physical activity.

	***

	-
	```

	It should also be able to do all that this can: https://huggingface.co/BigSalmon/InformalToFormalLincoln27

	Keywords to sentences or sentence.