Skip to content

internlm2模型为啥这么小 #607

Answered by SolenoidWGT
wangzhen38 asked this question in Q&A
Discussion options

You must be logged in to vote

hi您好,欢迎试用internlm2~

  1. 我们开源的20B模型是fp16的数据类型,采用了group query attention的结构,为了使参数量满足20B增大了intermediate_size的大小。发布的模型是没有经过量化操作的,最终的模型权重估算大小是: 20 * 10**9 * 2 / 1024 ** 3 = 37GB,应该是符合预期的。
  2. 如果您方便的话可以尝试用lmdeploy进行推理,我们对internlm的模型有针对性的推理优化。

Replies: 1 comment

Comment options

You must be logged in to vote
0 replies
Answer selected by ZwwWayne
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
question Further information is requested
2 participants
Converted from issue

This discussion was converted from issue #602 on January 17, 2024 11:44.