Josiefied-Qwen3-4B-abliterated-v1-GGUF w 128k context

#1225
by procapra - opened

You've uploaded a higher context version of the 8b josiefied qwen3, was curious if you could provide a 4b version?

I'm somewhat new to ai and hugging face, so I apologize if for some reason this is not possible or outside of your specific skillset.

We sure can try, no problem - only thing you could improve is provide the url to the model you quantized - I guess you mean https://huggingface.co/Goekdeniz-Guelmez/Josiefied-Qwen3-4B-abliterated-v1 ?

We have tried this model before, but I don't know why it failed back then, so I will try it again and at least can tell you why it didn't work - possibly the problem has been fixed since then.

No, actually, we already did this model and it was successful, that's why I don't have an error, so I have no clue what you are asking for at the moment.

Yeah that was the one, I didn't realize you already did it, that's my bad. Thanks anyway.

no problem, have fun on hf :)

Sign up or log in to comment