> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/ai-workbench/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/ai-workbench/_mcp/server.

> Provides information about the example projects for fine-tuning models

# Example Projects for Fine-Tuning Models

These example projects demonstrate how to fine-tune various large language models (LLMs) and image generation models using NVIDIA AI Workbench. The following projects highlight:

- Fine-tuning of popular open-source models including Llama 2, Llama 3, Mistral, Mixtral, and Phi-3.
- Parameter-efficient fine-tuning techniques with NeMo Framework.
- Customization of image generation models like SDXL.
- Best practices for model adaptation and optimization.

These examples are ideal for AI developers and researchers looking to:

- Adapt pre-trained models to specific use cases.
- Implement efficient fine-tuning strategies.
- Optimize model performance for specific tasks.
- Leverage NVIDIA's tools and frameworks for model customization.

| **Example Project on GitHub** | **Description** | **Clone and Open** | **Support Forum** |
|---|---|---|---|
| [Llama 2 Finetune](https://github.com/NVIDIA/workbench-example-llama2-finetune) | An example project to fine-tune Llama 2 | [Open in AI Workbench](https://ngc.nvidia.com/open-ai-workbench/aHR0cHM6Ly9naXRodWIuY29tL05WSURJQS93b3JrYmVuY2gtZXhhbXBsZS1sbGFtYTItZmluZXR1bmU=) | [Support forum link](https://forums.developer.nvidia.com/t/support-workbench-example-project-llama-2-finetune/278375) |
| [Llama 3 8b Finetune](https://github.com/NVIDIA/workbench-example-llama3-finetune) | An example project to fine-tune a Llama 3 8B Model | [Open in AI Workbench](https://ngc.nvidia.com/open-ai-workbench/aHR0cHM6Ly9naXRodWIuY29tL05WSURJQS93b3JrYmVuY2gtZXhhbXBsZS1sbGFtYTMtZmluZXR1bmU=) | [Support forum link](https://forums.developer.nvidia.com/t/support-workbench-example-project-llama-3-finetune/303411) |
| [Mistral Finetune](https://github.com/NVIDIA/workbench-example-mistral-finetune) | An example project to fine-tune a Mistral 7B model | [Open in AI Workbench](https://ngc.nvidia.com/open-ai-workbench/aHR0cHM6Ly9naXRodWIuY29tL05WSURJQS93b3JrYmVuY2gtZXhhbXBsZS1taXN0cmFsLWZpbmV0dW5l) | [Support forum link](https://forums.developer.nvidia.com/t/support-workbench-example-project-mistral-finetune/278376) |
| [Mixtral 8x7b Finetune](https://github.com/NVIDIA/workbench-example-mixtral-finetune) | An example project to fine-tune a Mixtral 8x7B Model | [Open in AI Workbench](https://ngc.nvidia.com/open-ai-workbench/aHR0cHM6Ly9naXRodWIuY29tL05WSURJQS93b3JrYmVuY2gtZXhhbXBsZS1taXh0cmFsLWZpbmV0dW5l) | [Support forum link](https://forums.developer.nvidia.com/t/support-workbench-example-project-mixtral-finetune/303413) |
| [NeMo Ptuning](https://github.com/NVIDIA/workbench-example-nemo-ptuning) | An example project to p-tune LLMs with NeMo Framework | [Open in AI Workbench](https://ngc.nvidia.com/open-ai-workbench/aHR0cHM6Ly9naXRodWIuY29tL05WSURJQS93b3JrYmVuY2gtZXhhbXBsZS1uZW1vLXB0dW5pbmc=) | [Support forum link](https://forums.developer.nvidia.com/t/support-workbench-example-project-nemo-p-tuning/278370) |
| [NeMo Punctuation](https://github.com/NVIDIA/workbench-example-nemo-punctuation) | An example project to annotate text with NeMo Framework | [Open in AI Workbench](https://ngc.nvidia.com/open-ai-workbench/aHR0cHM6Ly9naXRodWIuY29tL05WSURJQS93b3JrYmVuY2gtZXhhbXBsZS1uZW1vLXB1bmN0dWF0aW9u) | [Support forum link](https://forums.developer.nvidia.com/t/support-workbench-example-project-nemo-punctuation/278371) |
| [Nemotron Finetune](https://github.com/NVIDIA/workbench-example-nemotron-finetune) | An example project to fine-tune a Nemotron-3 8B model | [Open in AI Workbench](https://ngc.nvidia.com/open-ai-workbench/aHR0cHM6Ly9naXRodWIuY29tL05WSURJQS93b3JrYmVuY2gtZXhhbXBsZS1uZW1vdHJvbi1maW5ldHVuZQ==) | [Support forum link](https://forums.developer.nvidia.com/t/support-workbench-example-project-nemotron-finetune/278377) |
| [Phi-3 Mini Finetune](https://github.com/NVIDIA/workbench-example-phi3-finetune) | An example project to fine-tune a Phi-3 Mini Model | [Open in AI Workbench](https://ngc.nvidia.com/open-ai-workbench/aHR0cHM6Ly9naXRodWIuY29tL05WSURJQS93b3JrYmVuY2gtZXhhbXBsZS1waGkzLWZpbmV0dW5l) | [Support forum link](https://forums.developer.nvidia.com/t/support-workbench-example-project-phi-3-finetune/303412) |
| [SDXL Customization](https://github.com/NVIDIA/workbench-example-sdxl-customization) | An example project to customize an SDXL model | [Open in AI Workbench](https://ngc.nvidia.com/open-ai-workbench/aHR0cHM6Ly9naXRodWIuY29tL05WSURJQS93b3JrYmVuY2gtZXhhbXBsZS1zZHhsLWN1c3RvbWl6YXRpb24=) | [Support forum link](https://forums.developer.nvidia.com/t/support-workbench-example-project-sdxl-customization/278374) |

## Related Topics

- [Example Projects for Agentic AI](/ai-workbench/quickstart/example-agents)
- [Example Projects for Retrieval Augmented Generation (RAG)](/ai-workbench/quickstart/example-rag)
- [Example Projects for Data Science Workflows](/ai-workbench/quickstart/example-data-science)
- [Example Projects for Blueprint Workflows](/ai-workbench/quickstart/example-blueprints)
- [Example Projects using NIM Deployments](/ai-workbench/quickstart/example-nim)