The configuration files required for training and launching the OpenSoftware-World-OSW1 model have been uploaded. (The code was written by OpenSoftware-World.)
The “models/opensoftware-world-osw1:100m” folder has been created. (The OpenSoftware-World-OSW1 AI models will be released very soon—please stay tuned :D)
The “models/opensoftware-world-osw1:100m” folder has been created. (The OpenSoftware-World-OSW1 AI models will be released very soon—please stay tuned :D)
The “models/opensoftware-world-osw1:10m” folder has been created. (The OpenSoftware-World-OSW1 AI models will be released very soon—please stay tuned :D)
The “models/opensoftware-world-osw1:5m” folder has been created. (The OpenSoftware-World-OSW1 AI models will be released very soon—please stay tuned :D)
The “models/opensoftware-world-osw1:5m” folder has been created. (The OpenSoftware-World-OSW1 AI models will be released very soon—please stay tuned :D)
We have switched from the Regex tokenizer to the SentencePiece tokenizer. (The updated code was written by OpenSoftware-World and corrected by ChatGPT.)
Training code for the SentencePiece tokenizer for the OpenSoftware-World-OSW1 AI model. (This code was written by ChatGPT and edited by OpenSoftware-World.)