text: "Hey ,\n\nThank you for signing up for my weekly newsletter. Before we get started, you'll have to confirm your email address." example_title: "newsletter"
text: "Hi ,\n\nI hope this email finds you well. Let me start by saying that I am a big fan of your work." example_title: "fan"
text: "Greetings ,\n\nI hope you had a splendid evening at the Company sausage eating festival. I am reaching out because" example_title: "festival"
text: "Good Morning ,\n\nI was just thinking to myself about how much I love creating value" example_title: "value"
text: "URGENT - I need" example_title: "URGENT"

inference: parameters: min_length: 4 max_length: 64 length_penalty: 0.7 no_repeat_ngram_size: 3 do_sample: False num_beams: 4 early_stopping: True repetition_penalty: 3.5

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?

python

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

RichardErkhov/pszemraj_-_opt-350m-email-generation-4bits

Original model description:

inference: parameters: min_length: 4 max_length: 64 length_penalty: 0.7 no_repeat_ngram_size: 3 do_sample: False num_beams: 4 early_stopping: True repetition_penalty: 3.5

opt for email generation - 350M

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Framework versions

RichardErkhov/
pszemraj_-_opt-350m-email-generation-4bits