> For the complete documentation index, see [llms.txt](https://ai-docs.fptcloud.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ai-docs.fptcloud.com/fpt-ai-studio/faq.md). # FAQ ### 1. **Which model should I choose for fine-tuning?** * Small models (<=1B parameters) --> for testing or light workloads * Medium models (7B-13B) --> balanced performance and cost * Large models (30B+) --> for complex tasks, usually requires multi-node setup * Instruction-tuned models are preferred if your task is prompt-response based ### **2. How long does fine-tuning take?** It depends on: * Model size (a few hours for small models, several days for very large ones) * Dataset size * Your hardware setup (hyperparameters & infrastructure) Typically, it ranges from a few hours to several days. ### **3. What do your need to prepare before fine-tuning a model?** You'll need: * Strictly follow the expected dataset structure for the model you're fine-tuning. More details about Data sample, visit here: * Clean, diverse, and non-duplicated data. * A clear objective for fine-tuning (e.g., tech support, customer service, content writing, etc.). ### **4. How many GPUs do you need to fine-tune a model?** It depends on the model size: * <1B parameters: 1 GPU (24 GB VRAM) is sufficient * 7B models: 2-4 GPUs (40 GB VRAM each) * 13B models: 4-8 GPUs recommended * 30B+ models: Requires 8+ GPUs and multi-node setup ### **5. Do I need multiple nodes or just one node?** * For small to medium models (up to 13B), a single node with multiple GPUs is enough. * For larger models (30B+), multi-node setups are recommended for better memory and performance. ### **6. What is the minimum GPU memory required?** * At least **24GB VRAM per GPU** for standard fine-tuning * Without **LoRA/QLoRA methods**, you can fine-tune on GPUs with 8-16GB VRAM ### **7. Does the size of my training dataset affect hardware needs?** Yes. Larger datasets require more VRAM, RAM, and storage. * Datasets < 20GB --> can use **Managed volume** * Datasets > 20GB --> require **Dedicated network volume** --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://ai-docs.fptcloud.com/fpt-ai-studio/faq.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.