Update README.md
Browse files
README.md
CHANGED
|
@@ -4,9 +4,11 @@ language:
|
|
| 4 |
- ja
|
| 5 |
tags:
|
| 6 |
- translation
|
|
|
|
|
|
|
| 7 |
---
|
| 8 |
|
| 9 |
-
|
| 10 |
A Japanese-English and English-Japanese neural machine translation model, [webbigdata/C3TR-Adapter](https://huggingface.co/webbigdata/C3TR-Adapter), converted to gguf format so that it can run on a PC without a GPU.
|
| 11 |
|
| 12 |
現在のgguf版は翻訳後に幻覚を追加出力してしまう傾向があり、パラメーターを適宜調整する必要があります。
|
|
@@ -49,5 +51,4 @@ The following are the [recommended parameters](https://huggingface.co/google/gem
|
|
| 49 |
- -e (escape newlines (\n))
|
| 50 |
- --temp 0(pick most probable tokens)
|
| 51 |
- --repeat-penalty 1.0(disable repetition penalty (it's never a good idea to have this with instruction tuned models)
|
| 52 |
-
- --no-penalize-nl(do not penalize repeating newlines)
|
| 53 |
-
|
|
|
|
| 4 |
- ja
|
| 5 |
tags:
|
| 6 |
- translation
|
| 7 |
+
- gemma
|
| 8 |
+
- llama.cpp
|
| 9 |
---
|
| 10 |
|
| 11 |
+
Gemmaベースの日英、英日ニューラル機械翻訳モデルである[webbigdata/C3TR-Adapter](https://huggingface.co/webbigdata/C3TR-Adapter)をGPUがないPCでも動かせるようにggufフォーマットに変換したモデルです。
|
| 12 |
A Japanese-English and English-Japanese neural machine translation model, [webbigdata/C3TR-Adapter](https://huggingface.co/webbigdata/C3TR-Adapter), converted to gguf format so that it can run on a PC without a GPU.
|
| 13 |
|
| 14 |
現在のgguf版は翻訳後に幻覚を追加出力してしまう傾向があり、パラメーターを適宜調整する必要があります。
|
|
|
|
| 51 |
- -e (escape newlines (\n))
|
| 52 |
- --temp 0(pick most probable tokens)
|
| 53 |
- --repeat-penalty 1.0(disable repetition penalty (it's never a good idea to have this with instruction tuned models)
|
| 54 |
+
- --no-penalize-nl(do not penalize repeating newlines)
|
|
|