Andzejs Poprockis

Could i request another feature for hide? I mean i want to hide section or say a folder from navigation in the header but i also want to be able...

I think that this would be more realistic to do inside mattermost server app itself, because jistsi is just a standalone service that you connect to using a browser type...

what does the container logs say?

can you edit compose file to add `restart: always`. then run `docker compose up -d` then run `docker ps -a` then get the container id from the list of your...

What are your system specs? OS? CPU? RAM? Did you download model correctly? I mean maybe its corrupted, try downloading using browser, and then copy it to /models/ folder.

CPU seems to support AVX2.. Im running this in ubuntu VM, seems to load just fine. ``` HHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHH Checking discussions database... llama_model_load: loading model from './models/gpt4all-lora-quantized-ggml.bin' - please wait ......

> You got "bad magic" too. its most likely that the model loading script was updated because this UI relies and depends on other packages/repos, so if they get updated...

@Datou Hi, try this model, it works, the original model is messed up, idk why. ``` HHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHH Checking discussions database... llama_model_load: loading model from './models/ggml-vicuna-13b-4bit-rev1.bin' - please wait ... llama_model_load:...

For me it loaded after i pulled the newest changes from git and redownloaded `gpt4all-lora-quantized-ggml.bin` model

when?