You can deploy this model and start earning money today!

RichardErkhov/
postbot_-_distilgpt2-emailgen-gguf

Name: postbot_-_distilgpt2-emailgen-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

distilgpt2-emailgen - GGUF

Model creator: https://huggingface.co/postbot/
Original model: https://huggingface.co/postbot/distilgpt2-emailgen/

Name	Quant method	Size
distilgpt2-emailgen.Q2_K.gguf	Q2_K	0.06GB
distilgpt2-emailgen.IQ3_XS.gguf	IQ3_XS	0.07GB
distilgpt2-emailgen.IQ3_S.gguf	IQ3_S	0.07GB
distilgpt2-emailgen.Q3_K_S.gguf	Q3_K_S	0.07GB
distilgpt2-emailgen.IQ3_M.gguf	IQ3_M	0.07GB
distilgpt2-emailgen.Q3_K.gguf	Q3_K	0.07GB
distilgpt2-emailgen.Q3_K_M.gguf	Q3_K_M	0.07GB
distilgpt2-emailgen.Q3_K_L.gguf	Q3_K_L	0.07GB
distilgpt2-emailgen.IQ4_XS.gguf	IQ4_XS	0.07GB
distilgpt2-emailgen.Q4_0.gguf	Q4_0	0.08GB
distilgpt2-emailgen.IQ4_NL.gguf	IQ4_NL	0.08GB
distilgpt2-emailgen.Q4_K_S.gguf	Q4_K_S	0.08GB
distilgpt2-emailgen.Q4_K.gguf	Q4_K	0.08GB
distilgpt2-emailgen.Q4_K_M.gguf	Q4_K_M	0.08GB
distilgpt2-emailgen.Q4_1.gguf	Q4_1	0.08GB
distilgpt2-emailgen.Q5_0.gguf	Q5_0	0.09GB
distilgpt2-emailgen.Q5_K_S.gguf	Q5_K_S	0.09GB
distilgpt2-emailgen.Q5_K.gguf	Q5_K	0.09GB
distilgpt2-emailgen.Q5_K_M.gguf	Q5_K_M	0.09GB
distilgpt2-emailgen.Q5_1.gguf	Q5_1	0.09GB
distilgpt2-emailgen.Q6_K.gguf	Q6_K	0.1GB
distilgpt2-emailgen.Q8_0.gguf	Q8_0	0.12GB

Original model description:

license: apache-2.0 tags:

generated_from_trainer
distilgpt2
email generation
email datasets:
aeslc
postbot/multi_emails widget:
text: 'Good Morning Professor Beans,

Hope you are doing well. I just wanted to reach out and ask if differential calculus will be on the exam' example_title: email to prof
text: 'Hey ,

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 ,

I hope this email finds you well. I wanted to reach out and ask about office hours' example_title: office hours
text: 'Greetings ,

I hope you had a splendid evening at the Company sausage eating festival. I am reaching out because' example_title: festival
text: 'Good Morning Harold,

I was wondering when the next' example_title: event
text: URGENT - I need the TPS reports example_title: URGENT
text: 'Hi Archibald,

I hope this email finds you extremely well.' example_title: emails that find you
text: 'Hello there.

I just wanted to reach out and check in to' example_title: checking in
text: 'Hello ,

I hope this email finds you well. I wanted to reach out and see if you''ve enjoyed your time with us' example_title: work well
text: 'Hi ,

I hope this email finds you well. I wanted to reach out and see if we could catch up' example_title: catch up
text: I'm and I just moved into the area and wanted to reach out and get some details on where I could get groceries and example_title: grocery parameters: min_length: 4 max_length: 128 length_penalty: 0.8 no_repeat_ngram_size: 2 do_sample: false num_beams: 8 early_stopping: true repetition_penalty: 5.5 base_model: distilgpt2

distilgpt2-emailgen

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

python

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[0]['generated_text'])

try it in a Google Colab notebook
Use it in bash/cmd with this gist :)

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 distilgpt2 on a dataset of 50k emails, including the classic aeslc dataset.

It achieves the following results on the evaluation set:

Loss: 2.6247

Intended uses & limitations

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.

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: 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 results

Training Loss	Epoch	Step	Validation Loss
2.8299	1.0	248	2.7971
2.6984	2.0	496	2.6826
2.7022	3.0	744	2.6361
2.6436	4.0	992	2.6245
2.6195	5.0	1240	2.6247

Framework versions

Transformers 4.21.1
Pytorch 1.12.0+cu113
Datasets 2.4.0
Tokenizers 0.12.1

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	24.89
ARC (25-shot)	21.76
HellaSwag (10-shot)	27.52
MMLU (5-shot)	25.97
TruthfulQA (0-shot)	46.17
Winogrande (5-shot)	51.62
GSM8K (5-shot)	0.0
DROP (3-shot)	1.16

RichardErkhov/postbot_-_distilgpt2-emailgen-gguf