CyberClassic
Collection
This is a models for telegram bot - https://t.me/cyber_classic_bot
•
4 items
•
Updated
•
1
This model is implement sequence binary classifier for inference of score, that represent how much sequence is simillar to sequences from texts fo Dostovesky F.M. Base modle is Google T5 model, finetuned on dataset that contains 5700 sentences from the texts of Dostovesky F.M. with label 1, and 5771 sentences from the texts of Kuprin A.I. and sentences geenerated with RuGPT3.
Training parameters:
- Epoch = 12
- Learning Rate = 1e-3
- Optimizer = AdamW
- Scheduler = OneCycleLR
- Training env = PyTorch
- Downloads last month
- 18
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.