dahara1
/

gemma-2-9b-it-gguf-japanese-imatrix

Inference Endpoints

Model card Files Files and versions Community

dahara1 commited on Jul 20

Commit

d330960

•

1 Parent(s): 0f53f7a

Update README.md

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -19,6 +19,8 @@ Just to be on the safe side, I have uploaded both the 4-bit conventional convers
 再変換時に、9b版のみ重要度行列(iMatrix)に日本語データを更に追加しています。
 During reconversion, additional Japanese data was added to the importance matrix (iMatrix) for 9b only.
 gemma-2-9b-itを日本語が多く含まれる重要度行列(iMatrix)を使って量子化したgguf版です。日本語対応能力が多めに保持されている事を期待していますが確かめる事はまだ出来ていません
 This is a quantized gguf version of gemma-2-9b-it using an importance matrix (iMatrix) that contains many Japanese words. I hope it retains more Japanese support, but I can't be sure yet.

 再変換時に、9b版のみ重要度行列(iMatrix)に日本語データを更に追加しています。
 During reconversion, additional Japanese data was added to the importance matrix (iMatrix) for 9b only.
+## 本モデルについて about this model.
 gemma-2-9b-itを日本語が多く含まれる重要度行列(iMatrix)を使って量子化したgguf版です。日本語対応能力が多めに保持されている事を期待していますが確かめる事はまだ出来ていません
 This is a quantized gguf version of gemma-2-9b-it using an importance matrix (iMatrix) that contains many Japanese words. I hope it retains more Japanese support, but I can't be sure yet.