Table of Contents
Quickstart
# pip install transformers
from transformers import pipeline
def analyze_output(input: str):
pipe = pipeline("text-classification", model="Titeiiko/OTIS-Official-Spam-Model")
x = pipe(input)[0]
if x["label"] == "LABEL_0":
return {"type":"Not Spam", "probability":x["score"]}
else:
return {"type":"Spam", "probability":x["score"]}
print(analyze_output("C一eck out our amazin伞 b芯芯褧ting servi褋e 选here you can get to Leve訌 3 for 3 mont一s for just 20 USD."))
#Output: {'type': 'Spam', 'probability': 0.9996588230133057}
About The Project
Introducing Otis: Otis is an advanced anti-spam artificial intelligence model designed to mitigate and combat the proliferation of unwanted and malicious content within digital communication channels.
Contributing
Contributions are what make the open source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.
If you have a suggestion that would make this better, please fork the repo and create a pull request. You can also simply open an issue with the tag "enhancement". Don't forget to give the project a star! Thanks again!
- Fork the Project
- Create your Feature Branch (
git checkout -b JewishLewish/Otis) - Commit your Changes (
git commit -m 'Add some AmazingFeatures') - Push to the Branch (
git push origin JewishLewish/Otis) - Open a Pull Request
License
Distributed under the BSD-3 License. See LICENSE.txt for more information.
Contact
My Email: lenny@lunes.host
OtisV1
{'loss': 0.2879, 'learning_rate': 4.75e-05, 'epoch': 0.5}
{'loss': 0.1868, 'learning_rate': 4.5e-05, 'epoch': 1.0}
{'eval_loss': 0.23244266211986542, 'eval_runtime': 4.2923, 'eval_samples_per_second': 465.951, 'eval_steps_per_second': 58.244, 'epoch': 1.0}
{'loss': 0.1462, 'learning_rate': 4.25e-05, 'epoch': 1.5}
{'loss': 0.1244, 'learning_rate': 4e-05, 'epoch': 2.0}
{'eval_loss': 0.19869782030582428, 'eval_runtime': 4.5759, 'eval_samples_per_second': 437.075, 'eval_steps_per_second': 54.634, 'epoch': 2.0}
{'loss': 0.0962, 'learning_rate': 3.7500000000000003e-05, 'epoch': 2.5}
{'loss': 0.07, 'learning_rate': 3.5e-05, 'epoch': 3.0}
{'eval_loss': 0.18761929869651794, 'eval_runtime': 4.1205, 'eval_samples_per_second': 485.372, 'eval_steps_per_second': 60.672, 'epoch': 3.0}
{'loss': 0.0553, 'learning_rate': 3.2500000000000004e-05, 'epoch': 3.5}
{'loss': 0.0721, 'learning_rate': 3e-05, 'epoch': 4.0}
{'eval_loss': 0.19852963089942932, 'eval_runtime': 3.992, 'eval_samples_per_second': 501.004, 'eval_steps_per_second': 62.625, 'epoch': 4.0}
{'loss': 0.0447, 'learning_rate': 2.7500000000000004e-05, 'epoch': 4.5}
{'loss': 0.0461, 'learning_rate': 2.5e-05, 'epoch': 5.0}
{'eval_loss': 0.20028768479824066, 'eval_runtime': 3.8479, 'eval_samples_per_second': 519.766, 'eval_steps_per_second': 64.971, 'epoch': 5.0}
{'loss': 0.0432, 'learning_rate': 2.25e-05, 'epoch': 5.5}
{'loss': 0.033, 'learning_rate': 2e-05, 'epoch': 6.0}
{'eval_loss': 0.20464178919792175, 'eval_runtime': 3.9167, 'eval_samples_per_second': 510.638, 'eval_steps_per_second': 63.83, 'epoch': 6.0}
{'loss': 0.0356, 'learning_rate': 1.75e-05, 'epoch': 6.5}
{'loss': 0.027, 'learning_rate': 1.5e-05, 'epoch': 7.0}
{'eval_loss': 0.20742492377758026, 'eval_runtime': 3.9716, 'eval_samples_per_second': 503.578, 'eval_steps_per_second': 62.947, 'epoch': 7.0}
{'loss': 0.0225, 'learning_rate': 1.25e-05, 'epoch': 7.5}
{'loss': 0.0329, 'learning_rate': 1e-05, 'epoch': 8.0}
{'eval_loss': 0.20604351162910461, 'eval_runtime': 4.0244, 'eval_samples_per_second': 496.964, 'eval_steps_per_second': 62.12, 'epoch': 8.0}
{'loss': 0.0221, 'learning_rate': 7.5e-06, 'epoch': 8.5}
{'loss': 0.0127, 'learning_rate': 5e-06, 'epoch': 9.0}
{'eval_loss': 0.21241146326065063, 'eval_runtime': 3.9242, 'eval_samples_per_second': 509.659, 'eval_steps_per_second': 63.707, 'epoch': 9.0}
{'loss': 0.0202, 'learning_rate': 2.5e-06, 'epoch': 9.5}
{'loss': 0.0229, 'learning_rate': 0.0, 'epoch': 10.0}
{'eval_loss': 0.2140526920557022, 'eval_runtime': 3.9546, 'eval_samples_per_second': 505.743, 'eval_steps_per_second': 63.218, 'epoch': 10.0}
{'train_runtime': 667.0781, 'train_samples_per_second': 119.926, 'train_steps_per_second': 14.991, 'train_loss': 0.07010261821746826, 'epoch': 10.0}
- Downloads last month
- 31
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.