Instructions to use pszemraj/opt-350m-email-generation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pszemraj/opt-350m-email-generation with Transformers:

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

pipe = pipeline("text-generation", model="pszemraj/opt-350m-email-generation")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pszemraj/opt-350m-email-generation")
model = AutoModelForCausalLM.from_pretrained("pszemraj/opt-350m-email-generation")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use pszemraj/opt-350m-email-generation with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pszemraj/opt-350m-email-generation"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pszemraj/opt-350m-email-generation",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/pszemraj/opt-350m-email-generation

SGLang

How to use pszemraj/opt-350m-email-generation 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 "pszemraj/opt-350m-email-generation" \
    --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": "pszemraj/opt-350m-email-generation",
		"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 "pszemraj/opt-350m-email-generation" \
        --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": "pszemraj/opt-350m-email-generation",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use pszemraj/opt-350m-email-generation with Docker Model Runner:
```
docker model run hf.co/pszemraj/opt-350m-email-generation
```

opt for email generation - 350M

If you like the idea of wasting less time on emails, further work on this topic can be found on this hf org page

Why write the rest of your email when you can generate it?

from transformers import pipeline

model_tag = "pszemraj/opt-350m-email-generation"
generator = pipeline(
              'text-generation', 
              model=model_tag, 
              use_fast=False,
              do_sample=False,
              early_stopping=True,
            )
            
prompt = """
Hello, 

Following up on the bubblegum shipment."""

generator(
    prompt,
    max_length=64,
) # generate

Link to notebook on Colab

For this model, formatting matters. The results may be (significantly) different between the structure outlined above and prompt = "Hey, just wanted to ..." etc.

Model description

This model is a fine-tuned version of facebook/opt-350m on the aeslc dataset for six epochs.
Emails, phone numbers, etc., were attempted to be excluded in a dataset preparation step using clean-text in Python.
Note that API is restricted to generating 64 tokens - you can generate longer emails by using this in a text-generation pipeline object

Intended uses & limitations

in their everlasting wisdom, Facebook/Meta has decided to make a custom license for this, specifying several things. See facebook/opt-350m for details.

Training and evaluation data

the email_body field of train + validation (get more data) from the aeslc dataset.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 6e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
gradient_accumulation_steps: 16
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
num_epochs: 6

Framework versions

Transformers 4.19.2
Pytorch 1.11.0+cu113
Tokenizers 0.12.1

Downloads last month: 16

Safetensors

Model size

0.3B params

Tensor type

F32

pszemraj
/

opt-350m-email-generation