My first English model
I just made my first model! It's trained on a few mb of Wikipedia, isn't really good on it's own, I made it so others can fine-tune it. This is just a small 7m parameter model for now, I'm working on training a new larger version right now.
https://huggingface.co/simonko912/SLiNeP
it's already in the queue, let's hope it quants fast =)
You can check for progress at http://hf.tst.eu/status.html or regularly check the model
summary page at https://hf.tst.eu/model#SLiNeP-GGUF for quants to appear.
it's already in the queue, let's hope it quants fast =)
You can check for progress at http://hf.tst.eu/status.html or regularly check the model
summary page at https://hf.tst.eu/model#SLiNeP-GGUF for quants to appear.
Just asking, if it says ready it means what? It seems to say ready but there's no repo, I guess I'm still a beginner lol
it's downloaded but not started processing because it's waiting for other models to finish
it's downloaded but not started processing because it's waiting for other models to finish
Ah yes the small are last beacose they are super fast to generate
Why didn't they replace the phone keyboard algorithm with a ai model? Beacose I don't want it saying barcode instead of beacose lol
Higher PARAM models should have higher priority anyways, I can close this now lol
nah, we have a limit of how many quants we do in parallel, doesnt matter if you are a big model or small model. We have kind of priority, so one model has priority over another model, but obviously if I queued it late then it needs to wait for it's order
nah, we have a limit of how many quants we do in parallel, doesnt matter if you are a big model or small model. We have kind of priority, so one model has priority over another model, but obviously if I queued it late then it needs to wait for it's order
Ah, and also I noticed both the models done, thanks, I should have the different sizes done in a few days