[TRANSLATION] Add 7_inference and 8_agents EN-JA translation

[eltociear]

December 2024 Student Submission

Module Completed

• Module 1: Instruction Tuning
• Module 2: Preference Alignment
• Module 3: Parameter-efficient Fine-tuning
• Module 4: Evaluation
• Module 5: Vision-language Models
• Module 6: Synthetic Datasets
• Module 7: Inference
• Module 8: Deployment

Notebooks Added/Modified

List any notebooks you've added or modified:

• Added new example in module_name/student_examples/my_example.ipynb
• Modified existing notebook with additional examples
• Added documentation or comments

Checklist

• I have read the module materials
• My code runs without errors
• I have pushed models and datasets to the huggingface hub
• My PR is based on the december-2024 branch

Questions or Discussion Points

├── ja                     # I Added  
│   ├── 7_inference         
│   ├── 8_agents
│   └── ...
├── 7_inference   # Original directory       
└── 8_agents

Additional Notes

Any other information that might be helpful for reviewers:
The rest of the Japanese documentation has been added!

[burtenshaw]

Nice work on getting the whole course translated! Let me know when it's ready for review and I'll find a Japanese speaking reviewer.

[eltociear]

@burtenshaw
Thank you! This content is ready for review!

[hysts]

@eltociear
Here are a few things I noticed during a quick review.

1. Some parts of the text are garbled. For example, https://github.com/huggingface/smol-course/pull/194/files#diff-d5b5978c093eca5d6a60365e44513fc144c11d5986666949091302ddfe455dcbR57
   This notebook also has garbled text:
   https://github.com/huggingface/smol-course/pull/194/files#diff-bb7f6ee82642beac48a2a4a84458982ba2c05be28a0f9b0a26aaea446c2069a0
   The garbled text is also seen in your other PRs. For example,

   smol-course/ja/2_preference_alignment/README.md

   Line 27 in a5cc73e

   | DPOトレーニング | 直接選好最適化を使用してモデルを��レーニングする方法を学ぶ | 🐢 AnthropicのHH-RLHFデータセットを使用してモデルをトレーニングする<br>🐕 独自の選好データセットを使用する<br>🦁 さまざまな選好データセットとモデルサイズで実験する | [ノートブック](./notebooks/dpo_finetuning_example.ipynb) | <a target="_blank" href="https://colab.research.google.com/github/huggingface/smol-course/blob/main/2_preference_alignment/notebooks/dpo_finetuning_example.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a> |

2. These lines from the original text are missing in the translation:
   

   smol-course/8_agents/code_agents.md

   Lines 9 to 11 in a5cc73e

   	## Building Blocks of a Code Agent
   	Code agents are built on specialized language models fine-tuned for code understanding. These models are augmented with development tools like linters, formatters, and compilers to interact with real-world environments. Through retrieval techniques, agents maintain contextual awareness by accessing documentation and code histories to align with organizational patterns and standards. Action-oriented functions enable agents to perform concrete tasks such as committing changes or initiating merge requests.

3. This one is about another PR of yours [TRANSLATION] Add 1_instruction_tuning and 2_preference_alignment EN-JA translation #176, but the content of the two notebooks below is identical, except for garbled text in one of them:

   • https://github.com/huggingface/smol-course/blob/a5cc73e2e0a9df77d2c34369314431c94674a5dd/ja/1_instruction_tuning/notebooks/chat_templates_example.ipynb
   • https://github.com/huggingface/smol-course/blob/a5cc73e2e0a9df77d2c34369314431c94674a5dd/ja/1_instruction_tuning/notebooks/sft_finetuning_example.ipynb

   The former should be a translation of this notebook:
   https://github.com/huggingface/smol-course/blob/a5cc73e2e0a9df77d2c34369314431c94674a5dd/1_instruction_tuning/notebooks/chat_templates_example.ipynb

4. It seems that you've also translated the input text for the models into Japanese in code blocks. But many of the models used in this course are not good at handling Japanese, which can result in nonsensical output. So, translating the input text itself might not be appropriate. Would it be possible to include the translation as a comment instead?

[burtenshaw]

Thanks for the review @hysts!

@eltociear could you respond to the comments across all unit in this PR please.

[eltociear]

@hysts @burtenshaw
Thank you!
Please wait a moment while we confirm and respond to your content.

[whitphx]

Hi, thank you for the contribution!
Just let me point out the translations of proper nouns to avoid confusion, in addition to @hysts 's review above.

[whitphx]

Japanese translation of RAG is "検索拡張生成", not "取得強化生成"
Ref: https://aws.amazon.com/jp/what-is/retrieval-augmented-generation/, https://www.nri.com/jp/knowledge/glossary/rag.html