Update README.md
Browse files
README.md
CHANGED
@@ -18,20 +18,40 @@ This is a quantized gguf version of [google/gemma-2-2b-jpn-it](https://huggingfa
|
|
18 |
I hope it retains more Japanese support.
|
19 |
When [compared with the 4-bit quantized version of gemma-2-9b-it](https://huggingface.co/google/gemma-2-2b-jpn-it), we found that the perplexity score improved slightly.
|
20 |
|
21 |
-
# How to Use.
|
22 |
|
23 |
-
|
24 |
-
|
25 |
-
Please use a browser as Japanese characters will be garbled in the Windows 11 terminal (CMD, Power shell).
|
26 |
|
27 |
-
|
28 |
-
|
29 |
|
30 |
-
|
|
|
|
|
|
|
|
|
31 |
```
|
32 |
-
llama.cpp\build\bin\Release\llama-server -m .\gemma-2-
|
33 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
|
35 |
-
どのモデルを使うべきですか?
|
36 |
|
37 |
|
|
|
18 |
I hope it retains more Japanese support.
|
19 |
When [compared with the 4-bit quantized version of gemma-2-9b-it](https://huggingface.co/google/gemma-2-2b-jpn-it), we found that the perplexity score improved slightly.
|
20 |
|
21 |
+
# 使い方 How to Use.
|
22 |
|
23 |
+
ggufフォーマットに対応したツールは様々なものがあるのでお好きなツールをお使いください。例えば、[llama.cpp](https://github.com/ggerganov/llama.cpp)での使い方は以下です
|
24 |
+
There are many tools that support the gguf format, so please use the one you like. For example, the usage for [llama.cpp](https://github.com/ggerganov/llama.cpp) is as follows.
|
|
|
25 |
|
26 |
+
Windows11のターミナル(CMD, Power shell)では日本語が化けてしまうのでブラウザを使ってください
|
27 |
+
Please use a browser as Japanese characters will be garbled in the Windows 11 terminal (CMD, Power shell).
|
28 |
|
29 |
+
公式マニュアルに従ってllama.cppをビルドします
|
30 |
+
Build llama.cpp according to the official manual
|
31 |
+
|
32 |
+
ダウンロードしたモデルを指定して下記コマンドを実行します
|
33 |
+
Execute command.
|
34 |
```
|
35 |
+
llama.cpp\build\bin\Release\llama-server -m .\gemma-2-9b-it-Q4_K_M-fp16.gguf
|
36 |
```
|
37 |
+
ブラウザでhttp://127.0.0.1:8080を開きます
|
38 |
+
Open http://127.0.0.1:8080 in your browser
|
39 |
+
|
40 |
+
|
41 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/630469550907b9a115c91e62/PHli0VVox8bt6ziQoP02B.png)
|
42 |
+
|
43 |
+
|
44 |
+
# どのモデルを使うべきですか? Which model should I use?
|
45 |
+
|
46 |
+
人によって意見が異なりますが、目安としては以下です
|
47 |
+
- できればQ4以上
|
48 |
+
- メモリが許す限り大きいモデル(例えば、利用可能なメモリの7割程度)
|
49 |
+
|
50 |
+
Opinions vary from person to person, but here are some guidelines:
|
51 |
+
- Preferably Q4 or higher
|
52 |
+
- As large a model as memory allows (for example, about 70% of available memory)
|
53 |
+
|
54 |
+
|
55 |
|
|
|
56 |
|
57 |
|