llama
llama copied to clipboard
Does it support Chinese?
i have same question
i have the same question too, in llama paper i could not find any zh corpus
I have tested the Chinese support with the 7B model. Unfortunately, it seems the support of Chinese is extremely poor. (Perhaps increase the parameters can improve the performance in Chinese, but I have no ability to test)
I have tested the Chinese support with the 7B model. Unfortunately, it seems the support of Chinese is extremely poor. (Perhaps increase the parameters can improve the performance in Chinese, but I have no ability to test)
I think if the vocab contains chinese character, it is fine, we can fine-tuning it, but if it doesn't, it is hard to us to do more research in chinese
Hi, i have tried to fine-tune LLaMA model for better Chinese text generation. Please refer to: https://github.com/feizc/MLE-LLaMA
Closing this issues - Cool project @feizc !!