Update README.md
Browse files
README.md
CHANGED
@@ -16,11 +16,11 @@ tags:
|
|
16 |
C3TR-Adapter_ggufのVersion3を公開しました。
|
17 |
Version 3 of C3TR-Adapter_gguf has been released.
|
18 |
|
19 |
-
Version3はgoogle gemma-2ベースになり、一部の翻訳ベンチマークではgpt-4 turboやcommand-R plusを凌駕する品質です。
|
20 |
-
Version 3 is based on Google Gemma-2, and in some translation benchmarks, it outperforms GPT-4 Turbo and Command-R Plus.
|
21 |
|
22 |
-
以前のVersionのユーザーの方はプロンプトテンプレートに特殊なトークン(```<start_of_turn>, <end_of_turn>```)が追加されている事に注意してください
|
23 |
-
For users of previous versions, please note that special tokens(```<start_of_turn>, <end_of_turn>```) have been added to the prompt templates.
|
24 |
|
25 |
|
26 |
## 2024.05.18
|
@@ -45,7 +45,7 @@ You can try it using your browser with Colab, Google's free web service.
|
|
45 |
|
46 |
リンク先で[Open in Colab]ボタンを押してColabを起動してください
|
47 |
Press the [Open in Colab] button on the link to start Colab
|
48 |
-
[Colab Sample
|
49 |
|
50 |
### 利用可能なVersion(Available Versions)
|
51 |
|
@@ -79,7 +79,7 @@ make
|
|
79 |
|
80 |
英日翻訳(Translate English to Japanese)
|
81 |
```
|
82 |
-
./llama-cli -m
|
83 |
|
84 |
<start_of_turn>### Instruction:
|
85 |
Translate English to Japanese.
|
@@ -535,47 +535,33 @@ No, I protest this treatment!
|
|
535 |
|
536 |
日英翻訳時(Translate Japanese to English)
|
537 |
```
|
538 |
-
./llama-cli -m
|
539 |
|
540 |
-
|
541 |
-
Translate
|
542 |
When translating, please use the following hints:
|
543 |
-
[writing_style: casual
|
544 |
-
[
|
545 |
-
[
|
546 |
-
[hatsuharu_character_style: のじゃロリ]
|
547 |
|
548 |
### Input:
|
549 |
-
|
550 |
-
|
551 |
-
|
552 |
-
hatsuharu 'Bring me more sweets, will you?'
|
553 |
|
554 |
-
|
|
|
|
|
555 |
"
|
556 |
```
|
557 |
|
558 |
出力例(output)
|
559 |
```
|
560 |
-
|
561 |
-
Translate English to Japanese.
|
562 |
-
When translating, please use the following hints:
|
563 |
-
[writing_style: casual, game]
|
564 |
-
[hatsuharu: 初春]
|
565 |
-
[hatsuharu_first_person_and_ending: わらわ, なのじゃ]
|
566 |
-
[hatsuharu_character_style: のじゃロリ]
|
567 |
|
568 |
-
|
569 |
-
|
570 |
-
|
571 |
-
hatsuharu 'You can count on me. Hey, young one!'
|
572 |
-
hatsuharu 'Bring me more sweets, will you?'
|
573 |
-
|
574 |
-
### Response:
|
575 |
-
初春「また来たか、なのじゃ」
|
576 |
-
初春「まあ、しょうがないのじゃ。心配しないで、この艦隊を守るのじゃ」
|
577 |
-
初春「頼れるぞ。ねえ、若者」
|
578 |
-
初春「もっと菓子を持ってくるのじゃ」<eos> [end of text]
|
579 |
```
|
580 |
詳細は[webbigdata/C3TR-Adapter](https://huggingface.co/webbigdata/C3TR-Adapter)を参照してください
|
581 |
gguf版は一部の指定が動作しません
|
|
|
16 |
C3TR-Adapter_ggufのVersion3を公開しました。
|
17 |
Version 3 of C3TR-Adapter_gguf has been released.
|
18 |
|
19 |
+
Version3はgoogle gemma-2ベースになり、一部の翻訳ベンチマークではgpt-4 turboやcommand-R plusを凌駕する品質です。
|
20 |
+
Version 3 is based on Google Gemma-2, and in some translation benchmarks, it outperforms GPT-4 Turbo and Command-R Plus.
|
21 |
|
22 |
+
以前のVersionのユーザーの方はプロンプトテンプレートに特殊なトークン(```<start_of_turn>, <end_of_turn>```)が追加されている事に注意してください
|
23 |
+
For users of previous versions, please note that special tokens(```<start_of_turn>, <end_of_turn>```) have been added to the prompt templates.
|
24 |
|
25 |
|
26 |
## 2024.05.18
|
|
|
45 |
|
46 |
リンク先で[Open in Colab]ボタンを押してColabを起動してください
|
47 |
Press the [Open in Colab] button on the link to start Colab
|
48 |
+
[Colab Sample C3TR_Adapter_gguf_v3_Free_Colab_sample](https://github.com/webbigdata-jp/python_sample/blob/main/C3TR_Adapter_gguf_v3_Free_Colab_sample.ipynb)
|
49 |
|
50 |
### 利用可能なVersion(Available Versions)
|
51 |
|
|
|
79 |
|
80 |
英日翻訳(Translate English to Japanese)
|
81 |
```
|
82 |
+
./llama-cli -m ./C3TR-Adapter.f16.Q4_k_m.gguf -e --temp 0 --repeat-penalty 1.0 -n -2 -p "You are a highly skilled professional Japanese-English and English-Japanese translator. Translate the given text accurately, taking into account the context and specific instructions provided. Steps may include hints enclosed in square brackets [] with the key and value separated by a colon:. Only when the subject is specified in the Japanese sentence, the subject will be added when translating into English. If no additional instructions or context are provided, use your expertise to consider what the most appropriate context is and provide a natural translation that aligns with that context. When translating, strive to faithfully reflect the meaning and tone of the original text, pay attention to cultural nuances and differences in language usage, and ensure that the translation is grammatically correct and easy to read. After completing the translation, review it once more to check for errors or unnatural expressions. For technical terms and proper nouns, either leave them in the original language or use appropriate translations as necessary. Take a deep breath, calm down, and start translating.
|
83 |
|
84 |
<start_of_turn>### Instruction:
|
85 |
Translate English to Japanese.
|
|
|
535 |
|
536 |
日英翻訳時(Translate Japanese to English)
|
537 |
```
|
538 |
+
./llama-cli -m ./C3TR-Adapter.f16.Q4_k_m.gguf -e --temp 0 --repeat-penalty 1.0 -n -2 -p "You are a highly skilled professional Japanese-English and English-Japanese translator. Translate the given text accurately, taking into account the context and specific instructions provided. Steps may include hints enclosed in square brackets [] with the key and value separated by a colon:. Only when the subject is specified in the Japanese sentence, the subject will be added when translating into English. If no additional instructions or context are provided, use your expertise to consider what the most appropriate context is and provide a natural translation that aligns with that context. When translating, strive to faithfully reflect the meaning and tone of the original text, pay attention to cultural nuances and differences in language usage, and ensure that the translation is grammatically correct and easy to read. After completing the translation, review it once more to check for errors or unnatural expressions. For technical terms and proper nouns, either leave them in the original language or use appropriate translations as necessary. Take a deep breath, calm down, and start translating.
|
539 |
|
540 |
+
<start_of_turn>### Instruction:
|
541 |
+
Translate Japanese to English.
|
542 |
When translating, please use the following hints:
|
543 |
+
[writing_style: educational-casual]
|
544 |
+
[虎視虎子: Torako Koshi]
|
545 |
+
[鹿乃子のこ: Noko Shikanoko]
|
|
|
546 |
|
547 |
### Input:
|
548 |
+
都立日野南高校の虎視虎子は、近所や学校でも「お淑やかな優等生」と評判の女子高生だが、実は「中学までヤンキーで、高校デビューして優等生になった」ことを隠しながら生活していた。
|
549 |
+
|
550 |
+
ある日の登校中、虎子は頭にツノが生えている少女・鹿乃子のこが電線に引っ掛かっていたところを助ける。なぜか、のこに「元ヤン」であることを見破られた虎子は、「ヤンキーのお姉さん」と呼ばれるのが嫌で「こしたん」という愛称を受け入れる。
|
|
|
551 |
|
552 |
+
虎子は自分が「元ヤン」だと周囲にバレないように、虎子のクラスに転校してきたのこを警戒するが、のこの生態に振り回される中で、彼女が立ち上げた部活動「シカ部」の部長として、シカであるのこのお世話係になる。
|
553 |
+
<end_of_turn>
|
554 |
+
<start_of_turn>### Response:
|
555 |
"
|
556 |
```
|
557 |
|
558 |
出力例(output)
|
559 |
```
|
560 |
+
Torako Koshi, a high school student at Tokyo's Hino-Minami High School, is known as a "well-behaved honor student" by her neighbors and classmates. However, she's actually hiding the fact that she was a "delinquent" until middle school and became an honor student when she entered high school.
|
|
|
|
|
|
|
|
|
|
|
|
|
561 |
|
562 |
+
One day, while on her way to school, Torako sees a girl with horns on her head, Noko Shikanoko, hanging from a power line. She helps her, but somehow, Noko sees through Torako's disguise and calls her "a delinquent older sister." Torako hates being called that, so she accepts Noko's nickname, "Koshi-chan."
|
563 |
+
|
564 |
+
Torako tries to keep her past as a "delinquent" a secret, so she keeps an eye on Noko, who transferred to her class. However, she ends up taking care of Noko, who is a deer, as the president of the "Deer Club" that Noko started. [end of text]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
565 |
```
|
566 |
詳細は[webbigdata/C3TR-Adapter](https://huggingface.co/webbigdata/C3TR-Adapter)を参照してください
|
567 |
gguf版は一部の指定が動作しません
|