huggingface · DecodersLord · Mar 4, 2026
diff --git a/units/en/unit1/dummy-agent-library.mdx b/units/en/unit1/dummy-agent-library.mdx
@@ -20,6 +20,12 @@ We will use built-in Python packages like `datetime` and `os` so that you can tr
 
 You can follow the process [in this notebook](https://huggingface.co/agents-course/notebooks/blob/main/unit1/dummy_agent_library.ipynb) and **run the code yourself**.
 
+To run <a href="https://huggingface.co/agents-course/notebooks/blob/main/unit1/dummy_agent_library.ipynb" target="_blank">this notebook</a>, **you need a Hugging Face token** that you can get from <a href="https://hf.co/settings/tokens" target="_blank">https://hf.co/settings/tokens</a>.
+
+For more information on how to run Jupyter Notebooks, checkout <a href="https://huggingface.co/docs/hub/notebooks">Jupyter Notebooks on the Hugging Face Hub</a>.
+
+You also need to request access to <a href="https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct" target="_blank">the Meta Llama models</a>.
+
 ## Serverless API
 
 In the Hugging Face ecosystem, there is a convenient feature called Serverless API that allows you to easily run inference on many models. There's no installation or deployment required.

diff --git a/units/en/unit1/what-are-llms.mdx b/units/en/unit1/what-are-llms.mdx
@@ -211,10 +211,4 @@ That was a lot of information! We've covered the basics of what LLMs are, how th
 
 If you'd like to dive even deeper into the fascinating world of language models and natural language processing, don't hesitate to check out our <a href="https://huggingface.co/learn/nlp-course/chapter1/1" target="_blank">free NLP course</a>.
 
-Now that we understand how LLMs work, it's time to see **how LLMs structure their generations in a conversational context**.
-
-To run <a href="https://huggingface.co/agents-course/notebooks/blob/main/unit1/dummy_agent_library.ipynb" target="_blank">this notebook</a>, **you need a Hugging Face token** that you can get from <a href="https://hf.co/settings/tokens" target="_blank">https://hf.co/settings/tokens</a>.
-
-For more information on how to run Jupyter Notebooks, checkout <a href="https://huggingface.co/docs/hub/notebooks">Jupyter Notebooks on the Hugging Face Hub</a>.
-
-You also need to request access to <a href="https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct" target="_blank">the Meta Llama models</a>.
+Now that we understand how LLMs work, it's time to see **how LLMs structure their generations in a conversational context**.
diff --git a/units/es/unit1/dummy-agent-library.mdx b/units/es/unit1/dummy-agent-library.mdx
@@ -20,6 +20,12 @@ Utilizaremos paquetes integrados de Python como `datetime` y `os` para que pueda
 
 Puedes seguir el proceso [en este notebook](https://huggingface.co/agents-course/notebooks/blob/main/unit1/dummy_agent_library.ipynb) y **ejecutar el código tú mismo**.
 
+Para ejecutar <a href="https://huggingface.co/agents-course/notebooks/blob/main/unit1/dummy_agent_library.ipynb" target="_blank">este notebook</a>, **necesitas un token de Hugging Face** que puedes obtener de <a href="https://hf.co/settings/tokens" target="_blank">https://hf.co/settings/tokens</a>.
+
+Para más información sobre cómo ejecutar Jupyter Notebooks, consulta <a href="https://huggingface.co/docs/hub/notebooks">Jupyter Notebooks en el Hugging Face Hub</a>.
+
+También necesitas solicitar acceso a <a href="https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct" target="_blank">los modelos Meta Llama</a>.
+
 ## API Serverless
 
 En el ecosistema de Hugging Face, hay una característica conveniente llamada API Serverless que te permite ejecutar fácilmente inferencia en muchos modelos. No se requiere instalación ni despliegue.

diff --git a/units/es/unit1/what-are-llms.mdx b/units/es/unit1/what-are-llms.mdx
@@ -209,10 +209,4 @@ Exploraremos estos pasos con más detalle en esta Unidad, pero por ahora, lo que
 
 Si deseas profundizar aún más en el fascinante mundo de los modelos de lenguaje y el procesamiento del lenguaje natural, no dudes en consultar nuestro <a href="https://huggingface.co/learn/nlp-course/chapter1/1" target="_blank">curso gratuito de NLP</a>.
 
-Ahora que entendemos cómo funcionan los LLMs, es hora de ver **cómo los LLMs estructuran sus generaciones en un contexto conversacional**.
-
-Para ejecutar <a href="https://huggingface.co/agents-course/notebooks/blob/main/unit1/dummy_agent_library.ipynb" target="_blank">este notebook</a>, **necesitas un token de Hugging Face** que puedes obtener de <a href="https://hf.co/settings/tokens" target="_blank">https://hf.co/settings/tokens</a>.
-
-Para más información sobre cómo ejecutar Jupyter Notebooks, consulta <a href="https://huggingface.co/docs/hub/notebooks">Jupyter Notebooks en el Hugging Face Hub</a>.
-
-También necesitas solicitar acceso a <a href="https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct" target="_blank">los modelos Meta Llama</a>.
+Ahora que entendemos cómo funcionan los LLMs, es hora de ver **cómo los LLMs estructuran sus generaciones en un contexto conversacional**.
diff --git a/units/fr/unit1/dummy-agent-library.mdx b/units/fr/unit1/dummy-agent-library.mdx
@@ -18,6 +18,10 @@ Nous utiliserons des packages intégrés de Python tels que `datetime` et `os` a
 
 Vous pouvez suivre le processus [dans ce *notebook*](https://huggingface.co/agents-course/notebooks/blob/main/fr/unit1/dummy_agent_library.ipynb) et **exécuter le code vous-même**.
 
+Pour exécuter le <a href="https://huggingface.co/agents-course/notebooks/blob/main/fr/unit1/dummy_agent_library.ipynb" target="_blank"><i>notebook</i></a>, **vous avez besoin d'un *token* d'authentication Hugging Face** que vous pouvez obtenir sur la page <a href="https://hf.co/settings/tokens" target="_blank">https://hf.co/settings/tokens</a>.
+
+Vous devez également demander l'accès aux <a href="https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct" target="_blank">modèles Llama 3.2 de Meta</a>.
+
 ## API sans serveur
 
 Dans l'écosystème Hugging Face, il existe une fonctionnalité pratique appelée API sans serveur qui vous permet d'exécuter facilement des inférences sur de nombreux modèles. Aucune installation ou déploiement n'est requis.

diff --git a/units/fr/unit1/what-are-llms.mdx b/units/fr/unit1/what-are-llms.mdx
@@ -212,8 +212,4 @@ Cela fait beaucoup d'informations ! Nous avons couvert les bases de ce que sont
 
 Si vous souhaitez plonger encore plus profondément dans le monde fascinant des modèles de langage et du traitement du langage naturel, n'hésitez pas à consulter notre <a href="https://huggingface.co/learn/llm-course/fr/chapter1/1" target="_blank">cours gratuit sur le NLP</a>.
 
-Maintenant que nous comprenons le fonctionnement des LLM, il est temps de voir **comment ils structurent leurs générations dans un contexte conversationnel**.
-
-Pour exécuter le <a href="https://huggingface.co/agents-course/notebooks/blob/main/fr/unit1/dummy_agent_library.ipynb" target="_blank"><i>notebook</i></a>, **vous avez besoin d'un *token* d'authentication Hugging Face** que vous pouvez obtenir sur la page <a href="https://hf.co/settings/tokens" target="_blank">https://hf.co/settings/tokens</a>.
-
-Vous devez également demander l'accès aux <a href="https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct" target="_blank">modèles Llama 3.2 de Meta</a>.
+Maintenant que nous comprenons le fonctionnement des LLM, il est temps de voir **comment ils structurent leurs générations dans un contexte conversationnel**.
diff --git a/units/ko/unit1/dummy-agent-library.mdx b/units/ko/unit1/dummy-agent-library.mdx
@@ -20,6 +20,12 @@
 
 [이 노트북](https://huggingface.co/agents-course/notebooks/blob/main/dummy_agent_library.ipynb)에서 과정을 따라가며 **직접 코드를 실행**해볼 수 있습니다.
 
+<a href="https://huggingface.co/agents-course/notebooks/blob/main/dummy_agent_library.ipynb" target="_blank">이 노트북</a>을 실행하려면, **Hugging Face 토큰** 을 이곳에서  <a href="https://hf.co/settings/tokens" target="_blank">https://hf.co/settings/tokens</a> 발급하세요!
+
+Jupyter Notebook 실행 방법에 대한 자세한 내용은 <a href="https://huggingface.co/docs/hub/notebooks">Hugging Face Hub의 Jupyter Notebooks 문서</a>를 참고해주세요.
+
+또한, <a href="https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct" target="_blank"> Meta Llama 모델</a>에 대한 액세스를 요청해야 합니다.
+
 ## 서버리스 API [[serverless-api]]
 
 Hugging Face 생태계에는 다양한 모델에서 쉽게 추론을 실행할 수 있게 해주는 서버리스 API라는 편리한 기능이 있습니다. 별도의 설치나 배포 과정이 필요 없습니다.

diff --git a/units/ko/unit1/what-are-llms.mdx b/units/ko/unit1/what-are-llms.mdx
@@ -216,10 +216,4 @@ LLM은 사용자 명령을 해석하고, 대화의 문맥을 유지하며, 계
 
 언어 모델과 자연어 처리에 대해 더 깊이 공부하고 싶다면, Hugging Face의 <a href="https://huggingface.co/learn/nlp-course/chapter1/1" target="_blank">무료 NLP 강의 </a>를 확인해 보세요!
 
-이제 우리는 LLM이 어떻게 작동하는지에 대해 배웠으니, **LLM이 대화형 환경에서 어떻게 텍스트를 생성하는지** 살펴볼 차례입니다!
-
-<a href="https://huggingface.co/agents-course/notebooks/blob/main/dummy_agent_library.ipynb" target="_blank">이 노트북</a>을 실행하려면, **Hugging Face 토큰** 을 이곳에서  <a href="https://hf.co/settings/tokens" target="_blank">https://hf.co/settings/tokens</a> 발급하세요!
-
-Jupyter Notebook 실행 방법에 대한 자세한 내용은 <a href="https://huggingface.co/docs/hub/notebooks">Hugging Face Hub의 Jupyter Notebooks 문서</a>를 참고해주세요.
-
-또한, <a href="https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct" target="_blank"> Meta Llama 모델</a>에 대한 액세스를 요청해야 합니다.
+이제 우리는 LLM이 어떻게 작동하는지에 대해 배웠으니, **LLM이 대화형 환경에서 어떻게 텍스트를 생성하는지** 살펴볼 차례입니다!
diff --git a/units/ru-RU/unit1/dummy-agent-library.mdx b/units/ru-RU/unit1/dummy-agent-library.mdx
@@ -20,6 +20,12 @@
 
 Вы можете отслеживать процесс [в этом блокноте](https://huggingface.co/agents-course/notebooks/blob/main/unit1/dummy_agent_library.ipynb) и **запустите код самостоятельно**.
 
+Чтобы запустить <a href="https://huggingface.co/agents-course/notebooks/blob/main/unit1/dummy_agent_library.ipynb" target="_blank">этот блокнот</a>, **вам понадобится токен Hugging Face** который вы можете получить из <a href="https://hf.co/settings/tokens" target="_blank">https://hf.co/settings/tokens</a>.
+
+Более подробную информацию о том, как запустить блокноты Jupyter, изучите <a href="https://huggingface.co/docs/hub/notebooks">Блокноты Jupyter на Hugging Face Hub</a>.
+
+Вам также необходимо запросить доступ к <a href="https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct" target="_blank">модели Meta Llama</a>.
+
 ## Бессерверный API
 
 В экосистеме Hugging Face есть удобная функция Бессерверный API (Serverless API), которая позволяет легко выполнять инференс для многих моделей. При этом не требуется установки или развертывания.

diff --git a/units/ru-RU/unit1/what-are-llms.mdx b/units/ru-RU/unit1/what-are-llms.mdx
@@ -211,10 +211,4 @@ LLM являются ключевым компонентом агентов ис
 
 Если вы хотите еще глубже погрузиться в увлекательный мир языковых моделей и обработки естественного языка, не поленитесь ознакомиться с нашим <a href="https://huggingface.co/learn/nlp-course/chapter1/1" target="_blank">бесплатным курсом по NLP</a>.
 
-Теперь, когда мы поняли, как работают LLM, пришло время увидеть **как LLM структурируют свою генерацию в разговорном контексте**.
-
-Чтобы запустить <a href="https://huggingface.co/agents-course/notebooks/blob/main/unit1/dummy_agent_library.ipynb" target="_blank">этот блокнот</a>, **вам понадобится токен Hugging Face** который вы можете получить из <a href="https://hf.co/settings/tokens" target="_blank">https://hf.co/settings/tokens</a>.
-
-Более подробную информацию о том, как запустить блокноты Jupyter, изучите <a href="https://huggingface.co/docs/hub/notebooks">Блокноты Jupyter на Hugging Face Hub</a>.
-
-Вам также необходимо запросить доступ к <a href="https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct" target="_blank">модели Meta Llama</a>.
+Теперь, когда мы поняли, как работают LLM, пришло время увидеть **как LLM структурируют свою генерацию в разговорном контексте**.
diff --git a/units/vi/unit1/dummy-agent-library.mdx b/units/vi/unit1/dummy-agent-library.mdx
@@ -20,6 +20,12 @@ Chúng mình sẽ sử dụng các package Python tích hợp sẵn như `dateti
 
 Bạn có thể theo dõi quy trình [trong notebook này](https://huggingface.co/agents-course/notebooks/blob/main/unit1/dummy_agent_library.ipynb) và **tự chạy code**.
 
+Để chạy [notebook này](https://huggingface.co/agents-course/notebooks/blob/main/unit1/dummy_agent_library.ipynb), **bạn cần Hugging Face token** lấy từ [https://hf.co/settings/tokens](https://hf.co/settings/tokens).
+
+Xem thêm hướng dẫn chạy Jupyter Notebook tại [Jupyter Notebooks on the Hugging Face Hub](https://huggingface.co/docs/hub/notebooks).
+
+Bạn cũng cần xin quyền truy cập [model Meta Llama](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct).
+
 ## Serverless API
 
 Trong hệ sinh thái Hugging Face, có một tính năng tiện lợi gọi là Serverless API cho phép chạy inference trên nhiều mô hình dễ dàng. Không cần cài đặt hay triển khai.

diff --git a/units/vi/unit1/what-are-llms.mdx b/units/vi/unit1/what-are-llms.mdx
@@ -207,10 +207,4 @@ Thật nhiều thông tin! Ta đã điểm qua kiến thức cơ bản về LLM,
 
 Nếu muốn khám phá sâu hơn về mô hình ngôn ngữ và xử lý ngôn ngữ tự nhiên, đừng ngần ngại xem [khóa học NLP miễn phí](https://huggingface.co/learn/nlp-course/chapter1/1) của chúng tôi.
 
-Giờ đã hiểu cách LLM hoạt động, hãy xem **cách LLM cấu trúc output trong ngữ cảnh hội thoại**.
-
-Để chạy [notebook này](https://huggingface.co/agents-course/notebooks/blob/main/unit1/dummy_agent_library.ipynb), **bạn cần Hugging Face token** lấy từ [https://hf.co/settings/tokens](https://hf.co/settings/tokens).
-
-Xem thêm hướng dẫn chạy Jupyter Notebook tại [Jupyter Notebooks on the Hugging Face Hub](https://huggingface.co/docs/hub/notebooks).
-
-Bạn cũng cần xin quyền truy cập [model Meta Llama](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct).
+Giờ đã hiểu cách LLM hoạt động, hãy xem **cách LLM cấu trúc output trong ngữ cảnh hội thoại**.
diff --git a/units/zh-CN/unit1/dummy-agent-library.mdx b/units/zh-CN/unit1/dummy-agent-library.mdx
@@ -23,6 +23,12 @@
 
 你可以[在这个 notebook 中](https://huggingface.co/agents-course/notebooks/blob/main/unit1/dummy_agent_library.ipynb)跟随过程并**自己运行代码**。
 
+要运行<a href="https://huggingface.co/agents-course/notebooks/blob/main/unit1/dummy_agent_library.ipynb" target="_blank">这个笔记本</a>，**你需要一个 Hugging Face token**，你可以从<a href="https://hf.co/settings/tokens" target="_blank"> https://hf.co/settings/tokens </a>获取。
+
+有关如何运行 Jupyter Notebook 的更多信息，请查看<a href="https://huggingface.co/docs/hub/notebooks"> Hugging Face Hub 上的 Jupyter Notebook</a>。
+
+你还需要请求访问<a href="https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct" target="_blank"> Meta Llama 模型</a>。
+
 ## 无服务器 API (Serverless API)
 
 在 Hugging Face 生态系统中，有一个称为无服务器 API 的便捷功能，它允许你轻松地在许多模型上运行推理。不需要安装或部署。

diff --git a/units/zh-CN/unit1/what-are-llms.mdx b/units/zh-CN/unit1/what-are-llms.mdx
@@ -246,10 +246,4 @@ Transformer 架构的一个关键方面是**注意力机制**。在预测下一
 
 如果你想更深入地探索语言模型和自然语言处理这个迷人的世界，不妨查看我们的<a href="https://huggingface.co/learn/nlp-course/chapter1/1" target="_blank">免费 NLP 课程</a>。
 
-现在我们已经了解了大语言模型的工作原理，接下来是时候看看**大语言模型如何在对话语境中构建其生成内容**了。
-
-要运行<a href="https://huggingface.co/agents-course/notebooks/blob/main/unit1/dummy_agent_library.ipynb" target="_blank">这个笔记本</a>，**你需要一个 Hugging Face token**，你可以从<a href="https://hf.co/settings/tokens" target="_blank"> https://hf.co/settings/tokens </a>获取。
-
-有关如何运行 Jupyter Notebook 的更多信息，请查看<a href="https://huggingface.co/docs/hub/notebooks"> Hugging Face Hub 上的 Jupyter Notebook</a>。
-
-你还需要请求访问<a href="https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct" target="_blank"> Meta Llama 模型</a>。
+现在我们已经了解了大语言模型的工作原理，接下来是时候看看**大语言模型如何在对话语境中构建其生成内容**了。