Ok_Shape3437

joined 1 year ago
 

I'm having some trouble getting good results with an Exl2 4 bpw model. Is it simply worse than GPTQ 4 bit or maybe there's something wrong I'm doing?

 

I'm having some trouble getting good results with an Exl2 4 bpw model. Is it simply worse than GPTQ 4 bit or maybe there's something wrong I'm doing?

 

Portuguese is my mother tongue. I've tried ChatGPT, GPT 4, Claude, local LLMs, etc and they all produce inaccurate results that I still have to edit a lot. They also can't remember well if a character is male or female. It feels like they all have the same capabilities as Google Translate, which as far as I know, isn't an AI.

[–] Ok_Shape3437@alien.top 1 points 1 year ago