Ask it simple questions, this is my attempt on LMs ("AI") An RNN in testing combined with a Markov Chain ╰┈➤ (Feedback is really helpful!) The dataset is a bit too specific, making it answer general questions to be incoherent, specific prompts related to the dataset will make it introduce actually relavent results --- Try to prompt it with output it created or a part of it Example: "network", "markov", "what is up", “how are you” (it can do pretty well in greeting questions because those were first occurances) "tell me a joke" "hello" "hi" "what game" "roblox" "how are you today" "what is an ai language model" "minecraft" "i hate you- works better when unique mode" "what is up bro" "bro" and yes all from *dataset, no rule based things - (These were just random prompts I found) --- Info --- https://en.wikipedia.org/wiki/Recurrent_neural_network https://en.wikipedia.org/wiki/Markov_chain https://en.wikipedia.org/wiki/Shunting_yard_algorithm (for math solving, future use) --- Extras --- Use turbowarp for faster response times, but the model still works under scratch The model can answer alot of things. LSTMs are much better in these tasks, RNNs tend to "forget" because it applies weights and biases per everything, to add a form a weight connection between last inp you need LSTMs
Just thought this was cool All credits to RCSschoolAcc60
