deepseek-ai / deepseek-ai/DeepSeek-OCR

The efficiency of tokens compression

Open
#104 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
23.9k
Forks
2.2k
PR merge metrics
No merged PRs in 30d

Description

good job!

If visual tokens is used instead of text tokens, the efficiency of token generation should be a point worth considering, if used in the coding of LLM historical information.

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.