The model hallucinates after the first response
#2
by
LordFonDragon
- opened
I'm using Ollama to run the model, and for some reason it hallucinates after the first response, I think if it reaches a certain threshold of tokens, it starts hallucinating. What should I do? Is that my problem. or in the model itself?
别用ollama，你可你用python代码跑一遍再测一下，本人之前就是同模型，ollama的就比python的效果要差很多。
Is the website code used on chat.deepseek.com available to host locally? What would you recommend to run a gguf version locally?
本地，我用的pycharm。不建议，我不建议运行gguf版本，原汁原味儿的模型我觉得是最好的。