Why write the rest of your email when you can generate it?
from transformers import pipeline model_tag = "postbot/distilgpt2-emailgen" generator = pipeline( 'text-generation', model=model_tag, ) prompt = """ Hello, Following up on the bubblegum shipment.""" result = generator( prompt, max_length=64, do_sample=False, early_stopping=True, ) # generate print(result['generated_text'])
For this model, formatting matters. The results may be (significantly) different between the structure outlined above and
prompt = "Hey, just wanted to ..."etc.
This model is a fine-tuned version of distilgpt2 on a dataset of 50k emails, including the classic
It achieves the following results on the evaluation set:
- Loss: 2.6247
The intended use of this model is to provide suggestions to "autocomplete" the rest of your email. Said another way, it should serve as a tool to write predictable emails faster. It is not intended to write entire emails; at least some input is required to guide the direction of the model.
Please verify any suggestions by the model for A) False claims and B) negation statements before accepting/sending something.
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: 32
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.02
- num_epochs: 5
|Training Loss||Epoch||Step||Validation Loss|
- Transformers 4.21.1
- Pytorch 1.12.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1
- Downloads last month