opt-125m-email-generation/README.md

license, tags, datasets, widget, parameters, base_model

license	tags	datasets	widget	parameters	base_model
other	generated_from_trainer opt custom-license non-commercial email auto-complete 125m	aeslc	text example_title Hey <NAME>, Thank you for signing up for my weekly newsletter. Before we get started, you'll have to confirm your email address. newsletter text example_title Hi <NAME>, I hope this email finds you well. Let me start by saying that I am a big fan of your work. fan text example_title Greetings <NAME>, I hope you had a splendid evening at the Company sausage eating festival. I am reaching out because festival text example_title Good Morning <NAME>, I was just thinking to myself about how much I love creating value value text example_title URGENT - I need URGENT	min_length max_length length_penalty no_repeat_ngram_size do_sample num_beams early_stopping repetition_penalty use_fast 4 64 0.7 3 false 4 true 3.5 false	facebook/opt-125m

NOTE: there is currently a bug with huggingface API for OPT models. Please use the colab notebook to test :)

opt for email generation - 125m

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

from transformers import pipeline
model_tag = "pszemraj/opt-125m-email-generation"
generator = pipeline(
              'text-generation', 
              model=model_tag, 
              use_fast=False,
              do_sample=False,
            )
            
prompt = """
Hello, 
Following up on the bubblegum shipment."""
generator(
    prompt,
    max_length=96,
) # generate

• colab notebook for testing/use

About

This model is a fine-tuned version of facebook/opt-125m on an aeslc dataset.

• 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

It achieves the following results on the evaluation set:

• Loss: 2.5552

Intended uses & limitations

• OPT models cannot be used commercially
• here is a GitHub gist for a script to generate emails in the console or to a text file.

Training and evaluation data

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

Training results

Training Loss	Epoch	Step	Validation Loss
2.8245	1.0	129	2.8030
2.521	2.0	258	2.6343
2.2074	3.0	387	2.5595
2.0145	4.0	516	2.5552

Framework versions

• Transformers 4.20.1
• Pytorch 1.11.0+cu113
• Tokenizers 0.12.1