摘要:
open_llama_7b_v2 https://github.com/openlm-research/open_llama auto 多卡时,显存共 906M+3870M+3870M+762M == 9408 M ,大概率是 tf cuda 驱动的问题,倒腾下就正常了 3296M+3822M+38 阅读全文
摘要:
问题描述 运行代码会出现警告信息 numba cannot be imported and numba functions are disabled. Probably the execution is slow. Please install numba to gain a massive spe 阅读全文