You can deploy this model and start earning money today!

RichardErkhov/
postbot_-_gpt2-medium-emailgen-gguf

Name: postbot_-_gpt2-medium-emailgen-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

gpt2-medium-emailgen - GGUF

Model creator: https://huggingface.co/postbot/
Original model: https://huggingface.co/postbot/gpt2-medium-emailgen/

Name	Quant method	Size
gpt2-medium-emailgen.Q2_K.gguf	Q2_K	0.17GB
gpt2-medium-emailgen.IQ3_XS.gguf	IQ3_XS	0.18GB
gpt2-medium-emailgen.IQ3_S.gguf	IQ3_S	0.19GB
gpt2-medium-emailgen.Q3_K_S.gguf	Q3_K_S	0.19GB
gpt2-medium-emailgen.IQ3_M.gguf	IQ3_M	0.2GB
gpt2-medium-emailgen.Q3_K.gguf	Q3_K	0.21GB
gpt2-medium-emailgen.Q3_K_M.gguf	Q3_K_M	0.21GB
gpt2-medium-emailgen.Q3_K_L.gguf	Q3_K_L	0.23GB
gpt2-medium-emailgen.IQ4_XS.gguf	IQ4_XS	0.22GB
gpt2-medium-emailgen.Q4_0.gguf	Q4_0	0.23GB
gpt2-medium-emailgen.IQ4_NL.gguf	IQ4_NL	0.23GB
gpt2-medium-emailgen.Q4_K_S.gguf	Q4_K_S	0.23GB
gpt2-medium-emailgen.Q4_K.gguf	Q4_K	0.25GB
gpt2-medium-emailgen.Q4_K_M.gguf	Q4_K_M	0.25GB
gpt2-medium-emailgen.Q4_1.gguf	Q4_1	0.25GB
gpt2-medium-emailgen.Q5_0.gguf	Q5_0	0.27GB
gpt2-medium-emailgen.Q5_K_S.gguf	Q5_K_S	0.27GB
gpt2-medium-emailgen.Q5_K.gguf	Q5_K	0.29GB
gpt2-medium-emailgen.Q5_K_M.gguf	Q5_K_M	0.29GB
gpt2-medium-emailgen.Q5_1.gguf	Q5_1	0.29GB
gpt2-medium-emailgen.Q6_K.gguf	Q6_K	0.32GB
gpt2-medium-emailgen.Q8_0.gguf	Q8_0	0.41GB

Original model description:

license:

apache-2.0 tags:
text generation
emailgen
email generation
email datasets:
aeslc
postbot/multi-emails-100k

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 ,\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 ,\n\nI hope this email finds you well. I wanted to reach out and ask about office hours" example_title: "office hours"
text: "Greetings ,\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 Harold,\n\nI was wondering when the next" example_title: "event"
text: "URGENT - I need the TPS reports" example_title: "URGENT"
text: "Hi Archibald,\n\nI hope this email finds you extremely well." example_title: "emails that find you"
text: "Hello there.\n\nI just wanted to reach out and check in to" example_title: "checking in"
text: "Hello ,\n\nI 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 ,\n\nI 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: 32 max_length: 128 no_repeat_ngram_size: 2 do_sample: True temperature: 0.3 top_k: 20 top_p: 0.95 repetition_penalty: 3.5 length_penalty: 0.9

gpt2-medium-emailgen

colab

Why write the entire email when you can generate (most of) it?

python

from transformers import pipeline

model_tag = "postbot/gpt2-medium-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'])

about

This model is a fine-tuned version of gpt2-medium on the postbot/multi-emails-100k dataset. It achieves the following results on the evaluation set:

Loss: 1.5840

Model description

More information needed

Intended uses & limitations

this is intended as a tool to save time writing predictable emails and not to write emails without a human-in-the-loop. validate that your email is factually correct before sending it to others.

Training and evaluation data

the dataset is essentially a hand-curated/augmented expansion to the classic aeslc dataset

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.001
train_batch_size: 16
eval_batch_size: 16
seed: 42
distributed_type: multi-GPU
gradient_accumulation_steps: 8
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: 0.02
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
1.8701	1.0	789	1.8378
1.5065	2.0	1578	1.6176
1.1873	3.0	2367	1.5840

Framework versions

Transformers 4.22.2
Pytorch 1.10.0+cu113
Datasets 2.5.1
Tokenizers 0.12.1

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	25.97
ARC (25-shot)	26.45
HellaSwag (10-shot)	34.31
MMLU (5-shot)	24.1
TruthfulQA (0-shot)	43.96
Winogrande (5-shot)	50.43
GSM8K (5-shot)	0.0
DROP (3-shot)	2.53

RichardErkhov/postbot_-_gpt2-medium-emailgen-gguf