Johnny Arcitec

Speaking of the documentation; the main README describes `ollama pull` as `This command can also be used to update a local model. Only the diff will be pulled.` This is...

@DuckyBlender > maybe there should be a feature in ollama which allows easier RAG? Have you tried the RAG support here? https://github.com/open-webui/open-webui

Very good suggestion. All media centers have that feature. I haven't needed it often, but sometimes it is necessary.

> Perhaps provide a filelock that does not share between threads? The threads are fake. Python isn't freely multi-threaded. There's just 1 process in Python, and it only runs 1...

@WongKinYiu Okay but `mask = 1,2,3` & `mask = 3,4,5` is a bug. It's telling darknet to reuse mask 3 twice. The original author fixed it in the original config...

> in my experiments, i have trained yolo-v3-tiny more than five times using both of `mask = 1,2,3` & `mask = 3,4,5` and `mask = 0,1,2` & `mask = 3,4,5`...

Ohh okay! For any future readers, we're talking in two tickets at the same time now... and here's the thing WongKinYiu is referring to: https://github.com/AlexeyAB/darknet/issues/3380#issuecomment-542217703 So the yolo-v3-tiny (official) results...

@WongKinYiu Yeah we don't "need" to retrain it and we can still load the same weights with different mask settings... But doesn't the mAP go down if we re-use old...

@WongKinYiu Ohhhh, okay, really sorry for mixing up the words ImageNet and COCO, I forgot that your model weights were trained on COCO (with transfer learning from the `123` ImageNet...

Okay according to @pjreddie the `mask` controls which bounding boxes the layer is responsible for detecting. The lower mask numbers are the smallest objects. So the answer is: If we...