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

Libraries

How to use sagorsarker/emailgenerator with Transformers:

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

pipe = pipeline("text-generation", model="sagorsarker/emailgenerator")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sagorsarker/emailgenerator")
model = AutoModelForCausalLM.from_pretrained("sagorsarker/emailgenerator")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use sagorsarker/emailgenerator with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/sagorsarker/emailgenerator

SGLang

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

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

emailgenerator

Commit History

Adding `safetensors` variant of this model (#1)

76d1a90

sagorsarker

SFconvertbot commited on Mar 25, 2023

Update README.md

0405507

sagorsarker commited on Aug 8, 2022

Update README.md

2dd275e

sagorsarker commited on Aug 8, 2022

Update README.md

a666e09

sagorsarker commited on Apr 2, 2022

model files added

86400ac

sagorbrur commited on Mar 29, 2022

Update README.md

01ad74c

sagorsarker commited on Mar 29, 2022

initial commit

82da6ba

sagorsarker commited on Mar 29, 2022

Commit History

Adding `safetensors` variant of this model (#1) 76d1a90

Update README.md 0405507

Update README.md 2dd275e

Update README.md a666e09

model files added 86400ac

Update README.md 01ad74c

initial commit 82da6ba