Hansson0728

maybe add options for startup paramaters for llama cpp example prevent model from unloading from memory and stuff like that

> What is the use case for this? Is it causing a problem? Preventing offloading seems to me to be not an optimal solution, as it could easily cause resource...

i would say somehing like: ``` ` { "name": "codellama:13b", "modified_at": "2023-11-04T14:56:49.277302595-07:00", "size": 7365960935, "digest": "9f438cb9cd581fc025612d27f7c1a6669ff83a8bb0ed86c94fcf4c5440555697", "details": { "format": "gguf", "family": "llama", "families": null, "Type": 'LLM' ('Embedding') "parameter_size": "13B", "quantization_level":...

i did this to fix it: added a "sheep" prefix to the creation of div: this.id = "sheep" + Date.now() + Math.random(), to remove all sheeps var elements = document.querySelectorAll(`[id^="sheep"]`);...