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

Libraries

How to use jeffbritts/abstracts_to_post_model with Transformers:

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

pipe = pipeline("text-generation", model="jeffbritts/abstracts_to_post_model")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("jeffbritts/abstracts_to_post_model")
model = AutoModelForSeq2SeqLM.from_pretrained("jeffbritts/abstracts_to_post_model")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jeffbritts/abstracts_to_post_model with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/jeffbritts/abstracts_to_post_model

SGLang

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

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

YAML Metadata Warning:The pipeline tag "text2text-generation" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, audio-text-to-text, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-ranking, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, image-text-to-image, image-text-to-video, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, video-text-to-text, keypoint-detection, visual-document-retrieval, any-to-any, video-to-video, other

Model Card

Add more information here

Example Usage

from transformers import AutoModelForSeq2SeqLM, AutoTokenizer, pipeline

tokenizer = AutoTokenizer.from_pretrained('jeffbritts/abstracts_to_post_model', revision=None) # Load tokenizer
model = AutoModelForSeq2SeqLM.from_pretrained('jeffbritts/abstracts_to_post_model', revision=None) # Load model
pipe = pipeline('text2text-generation', model=model, tokenizer=tokenizer, pad_token_id=tokenizer.pad_token_id)

inputs = ["Acknowledgments\n\nThank you to all our donors. Their input was invaluable, and many of them have kept this program active. I really appreciate some privacy concerns with these papers and the paper itself. However, thank you to my research team for helping get the entire research protocol up and running since 2010. It's been absolutely stunning for me to be a part of such a small organization, but when something like this happens, it is such a huge deal. It means it's hard not to get involved.\n\nYou will also get a new Open Science Foundation letter if you donate and support NLP. I know I am more than qualified to help you in any way you get involved. Thank you in advance.\n\nAs an additional thanks-good-ness, at the risk of repeating some of a large list, I will do an accompanying Google Hangout. The Hangout is where you can send an email at nlp-doc@umass-edu. In my time as a speaker, we'll do an ongoing Hangout video series and maybe even a live talk. The original YouTube channel is hosted here.\n\nIf you have any questions or concerns or would like to talk to a team member, write to my Open Science Committee through this website below or send your comments directly to me. Thanks."]
print(pipe(inputs, max_length=512, do_sample=False))

This model was trained with a synthetic dataset with DataDreamer 🤖💤. The synthetic dataset card and model card can be found here. The training arguments can be found here.

Downloads last month: 3

Safetensors

Model size

0.2B params

Tensor type

F32

Model tree for jeffbritts/abstracts_to_post_model

Base model

google/t5-v1_1-base

Finetuned

(55)

this model