You can deploy this model and start earning money today!

RichardErkhov/
postbot_-_bloom-1b1-emailgen-gguf

Name: postbot_-_bloom-1b1-emailgen-gguf
Rating: 2.5 (87 reviews)

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

bloom-1b1-emailgen - GGUF

Model creator: https://huggingface.co/postbot/
Original model: https://huggingface.co/postbot/bloom-1b1-emailgen/

Name	Quant method	Size
bloom-1b1-emailgen.Q2_K.gguf	Q2_K	0.66GB
bloom-1b1-emailgen.IQ3_XS.gguf	IQ3_XS	0.73GB
bloom-1b1-emailgen.IQ3_S.gguf	IQ3_S	0.73GB
bloom-1b1-emailgen.Q3_K_S.gguf	Q3_K_S	0.73GB
bloom-1b1-emailgen.IQ3_M.gguf	IQ3_M	0.77GB
bloom-1b1-emailgen.Q3_K.gguf	Q3_K	0.79GB
bloom-1b1-emailgen.Q3_K_M.gguf	Q3_K_M	0.79GB
bloom-1b1-emailgen.Q3_K_L.gguf	Q3_K_L	0.82GB
bloom-1b1-emailgen.IQ4_XS.gguf	IQ4_XS	0.84GB
bloom-1b1-emailgen.Q4_0.gguf	Q4_0	0.87GB
bloom-1b1-emailgen.IQ4_NL.gguf	IQ4_NL	0.87GB
bloom-1b1-emailgen.Q4_K_S.gguf	Q4_K_S	0.87GB
bloom-1b1-emailgen.Q4_K.gguf	Q4_K	0.91GB
bloom-1b1-emailgen.Q4_K_M.gguf	Q4_K_M	0.91GB
bloom-1b1-emailgen.Q4_1.gguf	Q4_1	0.93GB
bloom-1b1-emailgen.Q5_0.gguf	Q5_0	0.99GB
bloom-1b1-emailgen.Q5_K_S.gguf	Q5_K_S	0.99GB
bloom-1b1-emailgen.Q5_K.gguf	Q5_K	1.02GB
bloom-1b1-emailgen.Q5_K_M.gguf	Q5_K_M	1.02GB
bloom-1b1-emailgen.Q5_1.gguf	Q5_1	1.05GB
bloom-1b1-emailgen.Q6_K.gguf	Q6_K	1.12GB
bloom-1b1-emailgen.Q8_0.gguf	Q8_0	1.45GB

Original model description:

license: bigscience-bloom-rail-1.0 tags:

text generation
generated_from_trainer
email generation
email
emailgen 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: "嘿\n\n感谢你注册我的每周通讯。在我们开始之前，你必须确认你的电子邮件地址。." example_title: "通讯"
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: "Grüße ,\n\nIch hoffe, du hattest einen schönen Abend beim Wurstessen der Firma. Ich melde mich, weil" example_title: "Wurstessen festival"
text: "Guten Morgen Harold,\n\nich habe mich gefragt, wann die nächste" example_title: "event"
text: "URGENT - I need the TPS reports" example_title: "URGENT"
text: "Hoi Archibald,\n\nik hoop dat deze e-mail je goed doet." example_title: "e-mails die je vinden"
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: "Jestem ,\n\nWłaśnie wprowadziłem się do obszaru i chciałem dotrzeć i uzyskać kilka szczegółów na temat tego, gdzie mogę dostać artykuły spożywcze i" example_title: "zakupy spożywcze" parameters: min_length: 32 max_length: 128 no_repeat_ngram_size: 2 do_sample: True temperature: 0.2 top_k: 20 top_p: 0.95 repetition_penalty: 3.5 length_penalty: 0.9

bloom-1b1-emailgen - v1

This model is a fine-tuned version of bigscience/bloom-1b1 on the postbot/multi-emails-100k dataset.

It achieves the following results on the evaluation set:

Loss: 1.7397

Model description

More information needed

Intended uses & limitations

⚠️ this model did not have any of the original layers frozen during training ⚠️

while this is still an area of investigation, the model likely needs to have some layers frozen during fine-tuning to retain the multilingual capabilities in balance with learning how to write emails.

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 7e-05
train_batch_size: 2
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
gradient_accumulation_steps: 64
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: 2.0

Training results

Training Loss	Epoch	Step	Validation Loss
1.8465	1.0	256	1.8656
1.4903	2.0	512	1.7396

details

***** eval metrics *****  

  epoch                   =        2.0  
  eval_loss               =     1.7397
  eval_runtime            = 0:04:27.41
  eval_samples            =       4216
  eval_samples_per_second =     15.766
  eval_steps_per_second   =     15.766
  perplexity              =     5.6956

Framework versions

Transformers 4.25.0.dev0
Pytorch 1.13.0+cu117
Datasets 2.6.1
Tokenizers 0.13.1

RichardErkhov/postbot_-_bloom-1b1-emailgen-gguf