Instructions to use deva-penumaka/distilgpt2-email-continuation-subject-and-body with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deva-penumaka/distilgpt2-email-continuation-subject-and-body with Transformers:

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

pipe = pipeline("text-generation", model="deva-penumaka/distilgpt2-email-continuation-subject-and-body")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deva-penumaka/distilgpt2-email-continuation-subject-and-body")
model = AutoModelForCausalLM.from_pretrained("deva-penumaka/distilgpt2-email-continuation-subject-and-body", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use deva-penumaka/distilgpt2-email-continuation-subject-and-body with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deva-penumaka/distilgpt2-email-continuation-subject-and-body"
# 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/distilgpt2-email-continuation-subject-and-body",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/deva-penumaka/distilgpt2-email-continuation-subject-and-body

SGLang

How to use deva-penumaka/distilgpt2-email-continuation-subject-and-body 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/distilgpt2-email-continuation-subject-and-body" \
    --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/distilgpt2-email-continuation-subject-and-body",
		"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/distilgpt2-email-continuation-subject-and-body" \
        --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/distilgpt2-email-continuation-subject-and-body",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use deva-penumaka/distilgpt2-email-continuation-subject-and-body with Docker Model Runner:
```
docker model run hf.co/deva-penumaka/distilgpt2-email-continuation-subject-and-body
```

distilgpt2-email-continuation-subject-and-body / README.md

deva-penumaka

Create README.md

028b0ee verified 7 days ago

preview code

Raw

History Blame Contribute Delete

1.01 kB

metadata

license: apache-2.0
datasets:
  - postbot/aeslc_kw
language:
  - en
metrics:
  - rouge
  - sacrebleu
  - bertscore
  - perplexity
base_model:
  - distilbert/distilgpt2
pipeline_tag: text-generation
library_name: transformers
tags:
  - distilgpt2
  - email
  - email-continuation
  - subject-and-body

This model is a fine-tuned version of distilbert/distilgpt2 for generating an email continuation using both the email subject and an incomplete email body.

Limitations

The model may:

Generate inaccurate or fabricated information Produce repetitive text Produce inappropriate or biased content Continue an email in a way that does not match the writer's intention Include names, facts, or commitments that were not present in the input

This model should not automatically send email or make decisions without human review.

Training data considerations

The model inherits limitations and biases from its base model and training dataset. Users should review the dataset and evaluate the model for their specific use case.