You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
* It is recommended that you tune the parameters for your task. Not doing so may result in choosing default parameters and eventually giving sub-optimal performace.
Quick Testing
I had fine-tuned the model on SPAM/HAM dataset. You can download it from here and follow the steps mentioned under Generation Text section.
Sample Results
SPAM: You have 2 new messages. Please call 08719121161 now. £3.50. Limited time offer. Call 090516284580.<|endoftext|>
SPAM: Want to buy a car or just a drink? This week only 800p/text betta...<|endoftext|>
SPAM: FREE Call Todays top players, the No1 players and their opponents and get their opinions on www.todaysplay.co.uk Todays Top Club players are in the draw for a chance to be awarded the £1000 prize. TodaysClub.com<|endoftext|>
SPAM: you have been awarded a £2000 cash prize. call 090663644177 or call 090530663647<|endoftext|>
HAM: Do you remember me?<|endoftext|>
HAM: I don't think so. You got anything else?<|endoftext|>
HAM: Ugh I don't want to go to school.. Cuz I can't go to exam..<|endoftext|>
HAM: K.,k:)where is my laptop?<|endoftext|>
Important Points to Note
Top-k and Top-p Sampling (Variant of Nucleus Sampling) has been used while decoding the sequence word-by-word. You can read more about it here
Note: First time you run, it will take considerable amount of time because of the following reasons -
Downloads pre-trained gpt2-medium model (Depends on your Network Speed)
Fine-tunes the gpt2 with your dataset (Depends on size of the data, Epochs, Hyperparameters, etc)
Fine-tuned pre-trained GPT2 for topic specific text generation. Such system can be used for Text Augmentation.