HODACHI commited on
Commit
beaaf42
·
verified ·
1 Parent(s): 40f6f6e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -3
README.md CHANGED
@@ -1,3 +1,11 @@
 
 
 
 
 
 
 
 
1
  # EZO model card
2
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/657e900beaad53ff67ba84db/0OYFqT8kACowa9bY1EZF6.png)
3
  **Terms of Use**: [Terms](https://www.kaggle.com/models/google/gemma/license/consent/verify/huggingface?returnModelRepoId=google/gemma-2-9b-it)
@@ -42,7 +50,7 @@ outputs = model.generate(input_ids=inputs.to(model.device), max_new_tokens=150)
42
  print(tokenizer.decode(outputs[0]))
43
  ```
44
 
45
- Template
46
  ```
47
  <bos><start_of_turn>user
48
  Write a hello world program<end_of_turn>
@@ -52,9 +60,10 @@ XXXXXX<end_of_turn><eos>
52
 
53
  ### Model Data
54
  Information about the data used for model training and how it was processed.
 
55
  #### Training Dataset
56
- We extracted high-quality data from Japanese Wikipedia and FineWeb to create instruction data. This diverse dataset ensures the model can handle a wide range of topics and languages, making it suitable for global use.
57
- 日本語のWikiデータおよび、FineWebから良質なデータのみを抽出し、Instructionデータを作成しました。この多様なデータセットにより、モデルは幅広いトピックと言語を扱うことができ、グローバルな使用に適しています。
58
  https://huggingface.co/datasets/legacy-datasets/wikipedia
59
  https://huggingface.co/datasets/HuggingFaceFW/fineweb
60
 
 
1
+ ---
2
+ license: gemma
3
+ library_name: transformers
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - conversational
7
+ ---
8
+
9
  # EZO model card
10
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/657e900beaad53ff67ba84db/0OYFqT8kACowa9bY1EZF6.png)
11
  **Terms of Use**: [Terms](https://www.kaggle.com/models/google/gemma/license/consent/verify/huggingface?returnModelRepoId=google/gemma-2-9b-it)
 
50
  print(tokenizer.decode(outputs[0]))
51
  ```
52
 
53
+ ### Template
54
  ```
55
  <bos><start_of_turn>user
56
  Write a hello world program<end_of_turn>
 
60
 
61
  ### Model Data
62
  Information about the data used for model training and how it was processed.
63
+
64
  #### Training Dataset
65
+ We extracted high-quality data from Japanese Wikipedia and FineWeb to create instruction data. Our innovative training approach allows for performance improvements across various languages and domains, making the model suitable for global use despite its focus on Japanese data.
66
+ 日本語のWikiデータおよび、FineWebから良質なデータのみを抽出し、Instructionデータを作成しました。このモデルでは日本語に特化させていますが、世界中のどんなユースケースでも利用可能なアプローチです。
67
  https://huggingface.co/datasets/legacy-datasets/wikipedia
68
  https://huggingface.co/datasets/HuggingFaceFW/fineweb
69