RicardoLee
/

Llama2-chat-Chinese-50W

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Resources

View closed (1)

此时不应降低学习率，warmup 等超参，而是应该放大到Pretrain 规模

#2 opened over 1 year ago by

那这个怎么调用呢

#1 opened over 1 year ago by