search

jiahe7ay / MINI_LLM

This is a repository used by individuals to experiment and reproduce the pre-training process of LLM.
348 stars 53 forks source link

大佬，qwen最接近的是1.8B,咋训出来1.4B的？ #6

Open daizehua1 opened 7 months ago

daizehua1 commented 7 months ago

大佬，qwen最接近的是1.8B,咋训出来1.4B的？

jiahe7ay commented 7 months ago

我改了qwen的配置文件

daizehua1 commented 7 months ago

感谢您的解答

daizehua1 commented 7 months ago

可以详细说一下修改的哪一部分吗

ye7love7 commented 6 months ago

同求，希望得到一个更大一点的模型，7B左右，求类似项目