openai

/

gpt-oss-20b

like 2.98k

Follow

OpenAI 17.1k

Try abliterated version

https://huggingface.co/bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF/blob/main/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-MXFP4_MOE.gguf

Try abliterated version

https://huggingface.co/bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF/blob/main/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-MXFP4_MOE.gguf

Thank you, I'll try it now!
Thank you for your feedback

Perhaps you know if there is a way to control her reasoning? their level.

I have LM Studio
it doesn't have Jinja in an open form like other models

I'm using llama.cpp(the backend of lm studio) directly

and this command can control the reasoning: --chat_template_kwargs "{\"reasoning_effort\":\"high\"}"

I'm using llama.cpp(the backend of lm studio) directly

and this command can control the reasoning: --chat_template_kwargs "{\"reasoning_effort\":\"high\"}"

Wow unbelievable, I didn't think he could be so smart.
even wrote all the commands correctly
wrote himself how to install Linux kernel headers, and drivers for the network adapter...

Thank You!