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

Quantization made by Richard Erkhov.

Github

Discord

Request more models

opt-350m-email-generation - bnb 4bits

• Model creator: https://huggingface.co/pszemraj/
• Original model: https://huggingface.co/pszemraj/opt-350m-email-generation/

Original model description:

license: other tags:

• generated_from_trainer
• opt
• custom-license
• no-commercial
• email
• auto-complete datasets:
• aeslc

widget:

• text: "Hey <NAME>,\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 <NAME>,\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 <NAME>,\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 <NAME>,\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?

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