why use shared codebook？ #18

Open

opened

训练visual tokenizer时，8级token共用一个codebook。在llm里面新增的反而是8*16k个visual tokenid，请问这是为啥呢～

Metadata

Assignees

No one assigned

Labels

No labels

No labels

Type

No type

Fields

No fields configured for issues without a type.

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests