Skip to content

Commit

Permalink
revise v3.0 vocab size
Browse files Browse the repository at this point in the history
  • Loading branch information
hiroshi-matsuda-rit authored Jul 5, 2024
1 parent e384942 commit cf5f1fc
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -34,7 +34,7 @@ v3.0b1のコードと英語の語彙は,Mistralの語彙を借用していま
| --- | --- | --- |
| code10K_en20K_ja30K.ver2.2 | 48,588 | コード,英語,日本語 |
| code20K_en40K_ja60K.ver2.2 | 96,869 | コード,英語,日本語 |
| **llm-jp-tokenizer-100k.ver3.0b1** | 99,487 | コード,英語,日本語,中国語,韓国語 |
| **llm-jp-tokenizer-100k.ver3.0b1** | 99,574 | コード,英語,日本語,中国語,韓国語 |


v3.0a2とv2.2の各モデルの分割性能を以下にまとめました.
Expand Down

0 comments on commit cf5f1fc

Please sign in to comment.