Instructions to use deva-penumaka/flan-t5-email-subject-generator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deva-penumaka/flan-t5-email-subject-generator with Transformers:

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

pipe = pipeline("text-generation", model="deva-penumaka/flan-t5-email-subject-generator")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("deva-penumaka/flan-t5-email-subject-generator")
model = AutoModelForSeq2SeqLM.from_pretrained("deva-penumaka/flan-t5-email-subject-generator", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use deva-penumaka/flan-t5-email-subject-generator with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/deva-penumaka/flan-t5-email-subject-generator

SGLang

How to use deva-penumaka/flan-t5-email-subject-generator 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 "deva-penumaka/flan-t5-email-subject-generator" \
    --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": "deva-penumaka/flan-t5-email-subject-generator",
		"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 "deva-penumaka/flan-t5-email-subject-generator" \
        --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": "deva-penumaka/flan-t5-email-subject-generator",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use deva-penumaka/flan-t5-email-subject-generator with Docker Model Runner:
```
docker model run hf.co/deva-penumaka/flan-t5-email-subject-generator
```

Model Card for Model ID

FLAN-T5 Email Subject Generator

This model is a fine-tuned version of google/flan-t5-small.

The model generates a concise email subject line from an email body.

Training dataset

The model was fine-tuned using:

Dataset: postbot/aeslc_kw
Input column: clean_email
Target column: subject_line
Dataset license: MIT

Model Details

Model Description

The source dataset repository describes itself as a cleaned version of AESLC with extracted keywords.

Input format

Inputs should use this prefix:

summarize this email as a subject line:

## Intended use

This model was created for an academic email subject-line generation project.

## Bias, Risks, and Limitations

The model may generate incomplete, inaccurate, or overly general subject lines.
It should not be used as the sole basis for handling sensitive email.


### Recommendations

Users (both direct and downstream) should be aware of the risks, biases and limitations of the model.

Downloads last month: 62

Safetensors

Model size

77M params

Tensor type

F32

Model tree for deva-penumaka/flan-t5-email-subject-generator

Base model

google/flan-t5-small

Finetuned

(505)

this model

deva-penumaka
/

flan-t5-email-subject-generator