gguf import stuck

[fastrizwaan]

https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2-GGUF/tree/main

i've download https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2.Q5_K_M.gguf

when adding using model creator, gguf, it is stuck there.

is there a simpler way to use gguf?

[stereomato]

Having the same issue here.

[Jeffser]

It just takes a while, it needs to upload the whole file to the Ollama instance, then Ollama processes it to make it a model

[stereomato]

Hm, I'm not sure. I saw an ollama serve process take some cpu time but right now, there's nothing from ollama using cpu time at all.

[Jeffser]

There's a window that is shown when a model fails to download / import, if nothing appears then it's still working on it.

Either way GGUF importing has always been a pain to get working so it wouldn't surprise me if it just gives up without returning an error

[stereomato]

I stopped Alpaca from adding the model, closed Alpaca, reopened it, tried to add the model again, and it worked!

[Jeffser]

well that's weird, glad it work tho hahaha

[stereomato]

I've cracked the code. Actually, if you don't fill in the "Tag" field, the GGUF model is never added. If you do, well, it is added quickly.