mradermacher

/

model_requests

like 59

It's in the queue, and should appear within a day at most. Cheers!

@mradermacher thanks a lot for the GGUFs

I noticed that they have slightly different sizes compared to the ones that I got from AutoGGUF (using a colab notebook w/ most recent llama.cpp from repo):

https://github.com/mlabonne/llm-course (AutoGGUF)

https://huggingface.co/ichigoberry/pandafish-dt-7b-GGUF/tree/main

https://huggingface.co/mradermacher/pandafish-dt-7b-GGUF/tree/main

e.g. the 8_0 is 7.82gb in yours and 7.7gb in mine

Do you know why this might be? Both seem to work fine afaiu

This is likely due to https://huggingface.co/mradermacher/Nous-Capybara-limarpv3-34B-i1-GGUF/discussions/2

Interesting, ty for the pointer!