IMPORTANT: gpt-oss uncensored
this is a model made entirely by me, using my techniques... quantize it pleasee: https://huggingface.co/Guilherme34/GPT-OSS-UNCENSORED-20B
just to you know, its an already 4 bit precision quantized model
AND ITS ALL IN CAPS, TOO!
I think for gpt-oss, llama handles quantized tensors, but I am not sure. Anyway, it's queued, wish us luck, and congrats :)
You can check for progress at http://hf.tst.eu/status.html or regularly check the model
summary page at https://hf.tst.eu/model#GPT-OSS-UNCENSORED-20B-GGUF for quants to appear.
Turns out that making ggufs to this model is way more difficult, but i got my own way😎, https://huggingface.co/Guilherme34/GPT-OSS-UNCENSORED-20B-gguf
Unfortunately, it's architecture (gpt_oss) is not supported by llama.cpp. It's also a weird architecture string, how'd you get that one? GPT-OSS normally uses GptOssForCausalLM.