Instructions to use 24NLPGroupO/EmailGeneration with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 24NLPGroupO/EmailGeneration with Transformers:

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

pipe = pipeline("text-generation", model="24NLPGroupO/EmailGeneration")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("24NLPGroupO/EmailGeneration")
model = AutoModelForCausalLM.from_pretrained("24NLPGroupO/EmailGeneration", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use 24NLPGroupO/EmailGeneration with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "24NLPGroupO/EmailGeneration"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "24NLPGroupO/EmailGeneration",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/24NLPGroupO/EmailGeneration

SGLang

How to use 24NLPGroupO/EmailGeneration 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 "24NLPGroupO/EmailGeneration" \
    --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": "24NLPGroupO/EmailGeneration",
		"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 "24NLPGroupO/EmailGeneration" \
        --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": "24NLPGroupO/EmailGeneration",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use 24NLPGroupO/EmailGeneration with Docker Model Runner:
```
docker model run hf.co/24NLPGroupO/EmailGeneration
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Model Card for Email Generation

Focused on generating emails based on features of the target user.

Model Details

Model Description

Final Project for Group O in 2024 Spring CS6120 NLP at Roux Institute, Northeastern University.

Developed by: Yun Cao, Yue Liu, Muyang Cheng, Nan Chen
Professor: Prashant Mittal
Model type: GPT2
Language(s) (NLP): Python, Transformers
Finetuned from model: postbot/distilgpt2-emailgen-V2

Model Sources [optional]

Repository: Final folder in Github CS6120NLP
Demo: Space link.

license: mit

datasets:

LightTai/personalized-email

language:

metrics:

rouge

tags: - email

Downloads last month: 13

24NLPGroupO
/

EmailGeneration

Model Card for Email Generation

Model Details

Model Description

Model Sources [optional]

tags: - email

Space using 24NLPGroupO/EmailGeneration 1