Keyvan Kambakhsh
Keyvan Kambakhsh
It would be good if people could store their entire model+descritption+training_data in a single file so that others could easily infer or fine tune them. Let's make femtoGPT a library!
Maybe create a tutorial for training a GPT model on Rust and put it on codeproject.com? Or somewhere similar?
We will need to have more clever methods of tokenization in femtoGPT. Possibly, it's good to have a SentencePiece model reader.
Find the best num-layers/embedding-degree/learning-rate/etc. in terms of accuracy and training time.
Right now, the code is very undocumented. As femtoGPT is also an educational library, it's good to have comprehensive guides, documentations and commentsm
Imagine someone sent a faulty (Or unwanted tx) to the network and it propagated to all nodes, user should be able to replace the faulty tx by sending a new...
GPU Processes can be very dangerous!