Llama-3_1-Nemotron-Ultra-253B-v1 imatrix iQ3 Abliterated or Uncensored

#872
by wa999 - opened

Llama-3_1-Nemotron-Ultra-253B-v1
iQ3_K_M imatrix Abliterated or Uncensored

It is supported by llama.cpp:
https://huggingface.co/nicoboss/Llama-3_1-Nemotron-Ultra-253B-v1-GGUF

https://huggingface.co/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1

No it is not yet suported by llama.cpp as https://github.com/ggml-org/llama.cpp/pull/12843 is not merged yet. I even mentioned this on the model card of my model you quoted.

For models larger than 70B like this one I have to rent GPUs on RunPod to uncensor which in this case would cost me at least $40. I really like this model so I might do so after extensive testing next weekend if I deam this model to be worth it and nobody else uncensored it by then but I can't promise it.

Your need to confirm your account before you can post a new comment.

Sign up or log in to comment