|
--- |
|
license: other |
|
tags: |
|
- generated_from_trainer |
|
- opt |
|
- custom-license |
|
- non-commercial |
|
- email |
|
- auto-complete |
|
- 125m |
|
datasets: |
|
- aeslc |
|
widget: |
|
- text: 'Hey <NAME>, |
|
|
|
|
|
Thank 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 <NAME>, |
|
|
|
|
|
I 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 <NAME>, |
|
|
|
|
|
I hope you had a splendid evening at the Company sausage eating festival. I am |
|
reaching out because' |
|
example_title: festival |
|
- text: 'Good Morning <NAME>, |
|
|
|
|
|
I was just thinking to myself about how much I love creating value' |
|
example_title: value |
|
- text: URGENT - I need |
|
example_title: URGENT |
|
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 |
|
use_fast: false |
|
base_model: facebook/opt-125m |
|
--- |
|
> NOTE: there is currently a bug with huggingface API for OPT models. Please use the [colab notebook](https://colab.research.google.com/gist/pszemraj/033dc9a38da31ced7a0343091ba42e31/email-autocomplete-demo-125m.ipynb) 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](https://colab.research.google.com/gist/pszemraj/033dc9a38da31ced7a0343091ba42e31/email-autocomplete-demo-125m.ipynb) for testing/use |
|
|
|
## About |
|
|
|
|
|
This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on an `aeslc` dataset. |
|
|
|
|
|
- Emails, phone numbers, etc., were attempted to be excluded in a dataset preparation step using [clean-text](https://pypi.org/project/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](https://gist.github.com/pszemraj/c1b0a76445418b6bbddd5f9633d1bb7f) 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](https://huggingface.co/datasets/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 |
|
|
