dahara1's picture
Update README.md
f182016 verified
|
raw
history blame
899 Bytes
gemma-2-9b-itγ‚’ζ—₯本θͺžγŒε€šγε«γΎγ‚Œγ‚‹ι‡θ¦εΊ¦θ‘Œεˆ—(iMatrix)γ‚’δ½Ώγ£γ¦ι‡ε­εŒ–γ—γŸggufη‰ˆγ§γ™γ€‚ζ—₯本θͺžε―ΎεΏœθƒ½εŠ›γŒε€šγ‚γ«δΏζŒγ•γ‚Œγ¦γ„γ‚‹δΊ‹γ‚’ζœŸεΎ…γ—γ¦γ„γΎγ™γŒη’Ίγ‹γ‚γ‚‹δΊ‹γ―まだ出ζ₯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.
## 使い方(How to use.)
[こけら](https://huggingface.co/dahara1/gemma-2-27b-it-gguf-japanese-imatrix)γ‚’γŠθͺ­γΏγγ γ•γ„
check [this page](https://huggingface.co/dahara1/gemma-2-27b-it-gguf-japanese-imatrix).
![image/png](https://cdn-uploads.huggingface.co/production/uploads/630469550907b9a115c91e62/-peoKA4fu1FZ1s0OcGexV.png)
![image/png](https://cdn-uploads.huggingface.co/production/uploads/630469550907b9a115c91e62/3x0AeGtFsPbxE4K_NXUPx.png)