dahara1 commited on
Commit
668e303
·
verified ·
1 Parent(s): bfef67e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -9
README.md CHANGED
@@ -20,9 +20,8 @@ tags:
20
  C3TR-AdapterのVersion3を公開しました。
21
  Version 3 of C3TR-Adapter has been released.
22
 
23
- このドキュメント等は現在、差し替え作業中で一部古いです。
24
- This documentation is currently being replaced and some parts are out of date.
25
-
26
 
27
  ## 2024.05.17
28
  [C3TR-AdapterのVersion2](https://huggingface.co/webbigdata/C3TR-Adapter/tree/version2)を公開しました。
@@ -57,8 +56,8 @@ For instructions on how to run the translation benchmark and other benchmark res
57
  GoogleのウェブサービスColabを使うと無料でC3TR-Adapterを試す事が出来ます。リンク先でOpen In Colabボタンを押して起動してください。
58
  You can try C3TR-Adapter for free using Google's web service Colab. Please press the Open In Colab button on the link to activate it.
59
 
60
- - [動作確認用の簡単なサンプル(A simple sample to check the operation)](https://github.com/webbigdata-jp/python_sample/blob/main/C3TR_Adapter_v2_Japanese_English_Translation_sample_code.ipynb)
61
- - [テキストファイルを一括で日英・英日翻訳するサンプル(Sample of batch translation of text files)](https://github.com/webbigdata-jp/python_sample/blob/main/C3TR_Adapter_v2_batch_translation_sample.ipynb)
62
  - [GPUがない環境でも動かす事ができるgguf版(A gguf version that can be run in environments without a GPU)](https://huggingface.co/webbigdata/C3TR-Adapter_gguf)
63
 
64
  ### モデルの動かし方(How to use Model)
@@ -78,8 +77,8 @@ If you want to run it on your own local computer, you will need at least approxi
78
  # example for windows user with CUDA 12.1.
79
  # pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121
80
 
81
- # Gemmaは最新のライブラリでなくては動かないので、以下のVersionに更新してください
82
- # Gemma will not work without the latest library, so please update to the following version
83
  pip install transformers==4.42.3
84
  pip install peft==0.11.1
85
  pip install bitsandbytes==0.43.1
@@ -96,7 +95,6 @@ from peft import PeftModel
96
  model_id = "unsloth/gemma-2-9b-it-bnb-4bit"
97
  peft_model_id = "webbigdata/C3TR-Adapter"
98
 
99
- # デバイスがbfloat16をサポートしているかどうかを確認
100
  if torch.cuda.is_available() and torch.cuda.get_device_capability(0)[0] >= 8:
101
  dtype = torch.bfloat16
102
  else:
@@ -475,7 +473,7 @@ Since today's meeting is very important, please arrive on time.
475
  You can specify the first person and ending for your character.
476
  This feature is still highly experimental and incomplete at this time.
477
 
478
- 映画「her」より一場面(A scene from the movie "Her")
479
  ```
480
  <start_of_turn>### Instruction:
481
  Translate English to Japanese.
 
20
  C3TR-AdapterのVersion3を公開しました。
21
  Version 3 of C3TR-Adapter has been released.
22
 
23
+ version3では4つのベンチマークのうち、1つでgpt4 turboを上回るという大幅な性能底上げが達成されています。
24
+ Version 3 achieved a significant performance boost, beating GPT4 Turbo in one of the four benchmarks.
 
25
 
26
  ## 2024.05.17
27
  [C3TR-AdapterのVersion2](https://huggingface.co/webbigdata/C3TR-Adapter/tree/version2)を公開しました。
 
56
  GoogleのウェブサービスColabを使うと無料でC3TR-Adapterを試す事が出来ます。リンク先でOpen In Colabボタンを押して起動してください。
57
  You can try C3TR-Adapter for free using Google's web service Colab. Please press the Open In Colab button on the link to activate it.
58
 
59
+ - [動作確認用の簡単なサンプル(A simple sample to check the operation)](https://github.com/webbigdata-jp/python_sample/blob/main/C3TR_Adapter_v3_Japanese_English_Translation_sample_code.ipynb)
60
+ - [テキストファイルを一括で日英・英日翻訳するサンプル(Sample of batch translation of text files)](https://github.com/webbigdata-jp/python_sample/blob/main/C3TR_Adapter_v3_batch_translation_sample.ipynb)
61
  - [GPUがない環境でも動かす事ができるgguf版(A gguf version that can be run in environments without a GPU)](https://huggingface.co/webbigdata/C3TR-Adapter_gguf)
62
 
63
  ### モデルの動かし方(How to use Model)
 
77
  # example for windows user with CUDA 12.1.
78
  # pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121
79
 
80
+ # Gemma 2は最新のライブラリでなくては動かないので、以下のVersionに更新してください
81
+ # Gemma 2 will not work without the latest library, so please update to the following version
82
  pip install transformers==4.42.3
83
  pip install peft==0.11.1
84
  pip install bitsandbytes==0.43.1
 
95
  model_id = "unsloth/gemma-2-9b-it-bnb-4bit"
96
  peft_model_id = "webbigdata/C3TR-Adapter"
97
 
 
98
  if torch.cuda.is_available() and torch.cuda.get_device_capability(0)[0] >= 8:
99
  dtype = torch.bfloat16
100
  else:
 
473
  You can specify the first person and ending for your character.
474
  This feature is still highly experimental and incomplete at this time.
475
 
476
+ 映画「her」より一場面(A scene from the movie "her")
477
  ```
478
  <start_of_turn>### Instruction:
479
  Translate English to Japanese.