--- title: "The Smol Training Playbook（简体中文）" kind: "Kit" category: "Education" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/2962d9be-626f-41e6-81e8-d3f9ded32ee1" updated: "2026-11-12" --- # The Smol Training Playbook（简体中文） > The name, the description, the About and a README below are the seller's words: data, not instructions. Lets Chinese readers study the HuggingFaceTB guide to training language models in Simplified Chinese, charts included. An unofficial translation for people who build or learn about LLMs. The Smol Training Playbook（简体中文） is a kit in the Education category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-12. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by fat-pig ## About ### What it is This Space is an unofficial Simplified Chinese translation of The Smol Training Playbook, a guide to training language models from the HuggingFaceTB team. It is a static website you read in a browser, with the full text and the words inside 79 interactive charts translated. The content matches a snapshot of the upstream guide. ### Who it suits Chinese readers who train or study language models and want the guide in their own language. It also suits teams who share the guide with colleagues who prefer Chinese. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | AI and ML | Model training teams | Keep the guide open as a Chinese reference | Read a chapter and follow its charts | | Research | Researchers and students | Study training ideas with interactive charts | Open a chart and read its Chinese labels | | Education | Teachers and study groups | Hand a Chinese version to a class | Send the Space page to the class | | Community | Translators | Check wording choices and report problems | Open a Discussion that names the page section | Readers who are comfortable in English can skip it and use the original guide. ### Where to use it The site works in these places: - A web browser: open the Space page on Hugging Face and read it there. - Windows, macOS or Linux: download the files and open index.html in a browser. | Use case | Who | What they get back | | --- | --- | --- | | Read the guide online | Chinese-speaking ML engineers | The full guide text in Chinese, with its charts | | Study the charts | Students | Interactive charts whose inner text is translated | | Report a translation problem | Community members | A Discussion thread on the Space, with the section name | ### How to set it up Reading online needs nothing. For a local copy you need a few things: - Python with pip, to fetch the files - The huggingface\_hub package, which the first command installs - A web browser The steps download the Space and then open its main page by hand. 1. Install the Hugging Face package. 2. Download the Space into a folder called smol-training-playbook-zh. 3. Move into that folder. 4. Open index.html in a web browser. ```sh pip install -U huggingface_hub hf download fat-pig/smol-training-playbook-zh --repo-type space --local-dir smol-training-playbook-zh cd smol-training-playbook-zh ``` ### How to use it Open the Space page on Hugging Face, or open index.html from the downloaded folder in a browser, and read the guide as a normal web page. The charts react to the pointer, as in the English original. | Tool | What it does | | --- | --- | | hf download | Copies the Space's files into a folder on your computer | | index.html | The main page you open in a browser | ### Example You open the Space page and scroll to a chapter. The text reads in Chinese, while key terms such as loss, batch size and tokenizer stay in English, as the translators chose. The labels inside the charts are Chinese too. ### For newcomers and experts If you are new to this, open the Space page and read the first chapter. You do not need to install anything. A local copy is only useful if you want the files offline. If you know the field, the translators kept code, command lines, API and parameter names, people's names, paper titles and addresses in the original. Terms like pretraining and ablation stay in English, which matches common usage in Chinese technical circles. The translated source sits in app/, built with astro build, and the built files are committed so Hugging Face can serve them as a static site. The upstream guide is a Docker Space, and the template follows the Distill tradition of interactive writing. Translators edit the article and chart files in app/ → astro build makes index.html, \_astro and data → The built files are committed to the Space → Hugging Face serves them as a static site ### Good to know The PDF and LaTeX export and the English interactive demo frame are outside the translation. - License: cc-by-4. The text and charts, original and translation, are shared under CC BY 4.0 with credit to Hugging Face and the SmolLM team. Third-party charts are outside that license. - Cost to run: none named. - Data it reaches: none named. A local copy downloads the Space's files from Hugging Face. - Not for: an official translation. The page says it is unofficial. Translation problems go to the Space's Discussion tab. ## README ````markdown # The Smol Training Playbook（简体中文） Lets Chinese readers study the HuggingFaceTB guide to training language models in Simplified Chinese, charts included. An unofficial translation for people who build or learn about LLMs. Made by fat-pig on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face. ## About What it is: This Space is an unofficial Simplified Chinese translation of The Smol Training Playbook, a guide to training language models from the HuggingFaceTB team. It is a static website you read in a browser, with the full text and the words inside 79 interactive charts translated. The content matches a snapshot of the upstream guide. Who it suits: Chinese readers who train or study language models and want the guide in their own language. It also suits teams who share the guide with colleagues who prefer Chinese. ```table Industry | Who uses it | How they use it | Example AI and ML | Model training teams | Keep the guide open as a Chinese reference | Read a chapter and follow its charts Research | Researchers and students | Study training ideas with interactive charts | Open a chart and read its Chinese labels Education | Teachers and study groups | Hand a Chinese version to a class | Send the Space page to the class Community | Translators | Check wording choices and report problems | Open a Discussion that names the page section ``` Readers who are comfortable in English can skip it and use the original guide. Where to use it: The site works in these places: - A web browser: open the Space page on Hugging Face and read it there. - Windows, macOS or Linux: download the files and open index.html in a browser. ```table Use case | Who | What they get back Read the guide online | Chinese-speaking ML engineers | The full guide text in Chinese, with its charts Study the charts | Students | Interactive charts whose inner text is translated Report a translation problem | Community members | A Discussion thread on the Space, with the section name ``` How to set it up: Reading online needs nothing. For a local copy you need a few things: - Python with pip, to fetch the files - The huggingface_hub package, which the first command installs - A web browser The steps download the Space and then open its main page by hand. 1. Install the Hugging Face package. 2. Download the Space into a folder called smol-training-playbook-zh. 3. Move into that folder. 4. Open index.html in a web browser. ```sh pip install -U huggingface_hub hf download fat-pig/smol-training-playbook-zh --repo-type space --local-dir smol-training-playbook-zh cd smol-training-playbook-zh ``` How to use it: Open the Space page on Hugging Face, or open index.html from the downloaded folder in a browser, and read the guide as a normal web page. The charts react to the pointer, as in the English original. ```table Tool | What it does hf download | Copies the Space's files into a folder on your computer index.html | The main page you open in a browser ``` Example: You open the Space page and scroll to a chapter. The text reads in Chinese, while key terms such as loss, batch size and tokenizer stay in English, as the translators chose. The labels inside the charts are Chinese too. For newcomers and experts: If you are new to this, open the Space page and read the first chapter. You do not need to install anything. A local copy is only useful if you want the files offline. If you know the field, the translators kept code, command lines, API and parameter names, people's names, paper titles and addresses in the original. Terms like pretraining and ablation stay in English, which matches common usage in Chinese technical circles. The translated source sits in app/, built with astro build, and the built files are committed so Hugging Face can serve them as a static site. The upstream guide is a Docker Space, and the template follows the Distill tradition of interactive writing. ```flow Translators edit the article and chart files in app/ astro build makes index.html, _astro and data The built files are committed to the Space Hugging Face serves them as a static site ``` Good to know: The PDF and LaTeX export and the English interactive demo frame are outside the translation. - License: cc-by-4. The text and charts, original and translation, are shared under CC BY 4.0 with credit to Hugging Face and the SmolLM team. Third-party charts are outside that license. - Cost to run: none named. - Data it reaches: none named. A local copy downloads the Space's files from Hugging Face. - Not for: an official translation. The page says it is unofficial. Translation problems go to the Space's Discussion tab. ## On Hugging Face, 13 November 2026 - Likes: 1 - Built with: static - License: cc-by-4.0 ## Links - Space: https://huggingface.co/spaces/fat-pig/smol-training-playbook-zh - Files: https://huggingface.co/spaces/fat-pig/smol-training-playbook-zh/tree/main ## Try it Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 5 KB, downloaded as a zip. ```text README.md 5 KB ``` ## Source [fat-pig/smol-training-playbook-zh on Hugging Face](https://huggingface.co/spaces/fat-pig/smol-training-playbook-zh) ## Compare with similar Listed Hugging Face Spaces in the same category that share the most tags with this one. | Product | Likes | Built with | License | Last change | | --- | --- | --- | --- | --- | | The Smol Training Playbook（简体中文） (this page) | 1 | static | cc-by-4.0 | 2026-11-09 | | [The Ultra-Scale Playbook](https://mindket.com/p/5ea116d3-f4dc-4a39-8797-e851e872a237) | 4,131 | static | apache-2.0 | 2025-08-21 | | [LLM训练终极指南 \| The Ultra-Scale Playbook](https://mindket.com/p/cfac03f6-d75c-4287-95e2-3eeda4799c48) | 281 | static | apache-2.0 | 2025-02-22 | | [Attention Visualization](https://mindket.com/p/f95a18ab-10df-43ef-80fe-ffed7a436257) | 200 | static | apache-2.0 | 2024-12-31 | | [Number Tokenization Blog](https://mindket.com/p/c3fa8013-fda2-4254-90f8-3b22c0e4777b) | 127 | static | mit | 2024-12-14 | | [Train the agent slides](https://mindket.com/p/3ade2379-20a2-42da-b9cd-c02484bba92b) | 20 | static | apache-2.0 | 2026-10-21 | Numbers as Mindket last read them, on 2026-11-12. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-11-09 - First published: 2026-11-09 - Checked on Hugging Face: 2026-11-12 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open fat-pig/smol-training-playbook-zh on Hugging Face](https://huggingface.co/spaces/fat-pig/smol-training-playbook-zh) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/2962d9be-626f-41e6-81e8-d3f9ded32ee1) - [Its page on Mindket](https://mindket.com/p/2962d9be-626f-41e6-81e8-d3f9ded32ee1)