<div align="center">
<img alt="jetson" width="1200px" src="https://files.seeedstudio.com/wiki/reComputer-Jetson/jetson-examples/Jetson1200x300.png">
</div>
# jetson-examples
[![Discord](https://dcbadge.vercel.app/api/server/5BQCkty7vN?style=flat&compact=true)](https://discord.gg/5BQCkty7vN)
This repository provides examples for running AI models and applications on NVIDIA Jetson devices. For generative AI, it supports a variety of examples including text generation, image generation, vision transformers, vector databases, and audio models.
To run the examples, you need to install the jetson-examples package and use the Seeed Studio [reComputer](https://www.seeedstudio.com/reComputer-J4012-p-5586.html), the edge AI device powered by Jetson Orin. The repo aims to make it easy to deploy state-of-the-art AI models, with just one line of command, on Jetson devices for tasks like language understanding, computer vision, and multimodal processing.
This repo builds upon the work of the [Jetson Containers](https://github.com/dusty-nv/jetson-containers), which provides a modular container build system for various AI/ML packages on NVIDIA Jetson devices. It also leverages resources and tutorials from the [Jetson Generative AI Lab](https://www.jetson-ai-lab.com/index.html), which showcases bringing generative AI to the edge, powered by Jetson hardware.
## Install
```sh
pip install jetson-examples
```
- [more installation methods](./docs/install.md)
- If you have already installed, you can use `pip install jetson-examples --upgrade` to update.
## Quickstart
To run and chat with [LLaVA](https://www.jetson-ai-lab.com/tutorial_llava.html):
```sh
reComputer run llava
```
## Example list
reComputer supports a list of examples from [jetson-ai-lab](https://www.jetson-ai-lab.com/)
Here are some examples that can be run:
| Example | Type | Model/Data Size | Image Size | Command |
| ------------------------------------------------ | ------------------------ | --------------- | ---------- | --------------------------------------- |
| 🆕 llama3 | Text (LLM) | 4.9GB | 10.5GB | `reComputer run llama3` |
| 🆕 [ollama](https://github.com/ollama/ollama) | Inference Server | * | 10.5GB | `reComputer run ollama` |
| LLaVA | Text + Vision (VLM) | 13GB | 14.4GB | `reComputer run llava` |
| Live LLaVA | Text + Vision (VLM) | 13GB | 20.3GB | `reComputer run live-llava` |
| stable-diffusion-webui | Image Generation | 3.97G | 7.3GB | `reComputer run stable-diffusion-webui` |
| nanoowl | Vision Transformers(ViT) | 613MB | 15.1GB | `reComputer run nanoowl` |
| [nanodb](../reComputer/scripts/nanodb/readme.md) | Vector Database | 76GB | 7.0GB | `reComputer run nanodb` |
| whisper | Audio | 1.5GB | 6.0GB | `reComputer run whisper` |
> Note: You should have enough space to run example, like `LLaVA`, at least `27.4GB` totally
More Examples can be found [examples.md](./docs/examples.md)
Want to add a Example by yourself? Check this [develop.md](./docs/develop.md)
## TODO List
- [ ] check disk space enough or not before run
- [ ] allow to setting some configs, such as `BASE_PATH`
- [ ] detect host environment and install what we need
- [ ] support jetson-containers update
- [ ] all type jetson support checking list
- [ ] better table to show example's difference
- [ ] try jetpack 6.0
Raw data
{
"_id": null,
"home_page": null,
"name": "jetson-examples",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "llama, llava, gpt, llm, nvidia, jetson, multimodal, jetson orin",
"author": null,
"author_email": "luozhixin <zhixin.luo@seeed.cc>",
"download_url": "https://files.pythonhosted.org/packages/b6/eb/5255986dfbc0aca8fce9dcff44a32114d41f710111dcfb9e10e1d4436a69/jetson_examples-0.0.7.tar.gz",
"platform": null,
"description": "<div align=\"center\">\n <img alt=\"jetson\" width=\"1200px\" src=\"https://files.seeedstudio.com/wiki/reComputer-Jetson/jetson-examples/Jetson1200x300.png\">\n</div>\n\n# jetson-examples\n\n[![Discord](https://dcbadge.vercel.app/api/server/5BQCkty7vN?style=flat&compact=true)](https://discord.gg/5BQCkty7vN)\n\nThis repository provides examples for running AI models and applications on NVIDIA Jetson devices. For generative AI, it supports a variety of examples including text generation, image generation, vision transformers, vector databases, and audio models.\nTo run the examples, you need to install the jetson-examples package and use the Seeed Studio [reComputer](https://www.seeedstudio.com/reComputer-J4012-p-5586.html), the edge AI device powered by Jetson Orin. The repo aims to make it easy to deploy state-of-the-art AI models, with just one line of command, on Jetson devices for tasks like language understanding, computer vision, and multimodal processing.\n\nThis repo builds upon the work of the [Jetson Containers](https://github.com/dusty-nv/jetson-containers), which provides a modular container build system for various AI/ML packages on NVIDIA Jetson devices. It also leverages resources and tutorials from the [Jetson Generative AI Lab](https://www.jetson-ai-lab.com/index.html), which showcases bringing generative AI to the edge, powered by Jetson hardware.\n\n## Install\n\n```sh\npip install jetson-examples\n```\n\n- [more installation methods](./docs/install.md)\n- If you have already installed, you can use `pip install jetson-examples --upgrade` to update.\n\n## Quickstart\n\nTo run and chat with [LLaVA](https://www.jetson-ai-lab.com/tutorial_llava.html):\n\n```sh\nreComputer run llava\n```\n\n## Example list\n\nreComputer supports a list of examples from [jetson-ai-lab](https://www.jetson-ai-lab.com/)\n\nHere are some examples that can be run:\n\n| Example | Type | Model/Data Size | Image Size | Command |\n| ------------------------------------------------ | ------------------------ | --------------- | ---------- | --------------------------------------- |\n| \ud83c\udd95 llama3 | Text (LLM) | 4.9GB | 10.5GB | `reComputer run llama3` |\n| \ud83c\udd95 [ollama](https://github.com/ollama/ollama) | Inference Server | * | 10.5GB | `reComputer run ollama` |\n| LLaVA | Text + Vision (VLM) | 13GB | 14.4GB | `reComputer run llava` |\n| Live LLaVA | Text + Vision (VLM) | 13GB | 20.3GB | `reComputer run live-llava` |\n| stable-diffusion-webui | Image Generation | 3.97G | 7.3GB | `reComputer run stable-diffusion-webui` |\n| nanoowl | Vision Transformers(ViT) | 613MB | 15.1GB | `reComputer run nanoowl` |\n| [nanodb](../reComputer/scripts/nanodb/readme.md) | Vector Database | 76GB | 7.0GB | `reComputer run nanodb` |\n| whisper | Audio | 1.5GB | 6.0GB | `reComputer run whisper` |\n\n> Note: You should have enough space to run example, like `LLaVA`, at least `27.4GB` totally\n\nMore Examples can be found [examples.md](./docs/examples.md)\n\nWant to add a Example by yourself? Check this [develop.md](./docs/develop.md)\n\n## TODO List\n\n- [ ] check disk space enough or not before run\n- [ ] allow to setting some configs, such as `BASE_PATH`\n- [ ] detect host environment and install what we need\n- [ ] support jetson-containers update\n- [ ] all type jetson support checking list\n- [ ] better table to show example's difference\n- [ ] try jetpack 6.0\n",
"bugtrack_url": null,
"license": null,
"summary": "Running Gen AI models and applications on NVIDIA Jetson devices with one-line command",
"version": "0.0.7",
"project_urls": {
"Homepage": "https://github.com/Seeed-Projects/jetson-examples",
"Issues": "https://github.com/Seeed-Projects/jetson-examples/issues"
},
"split_keywords": [
"llama",
" llava",
" gpt",
" llm",
" nvidia",
" jetson",
" multimodal",
" jetson orin"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "0b950a0a9bdadaf6f6011c690d24d633bcb9dca387dc0e6bbdb4654a087d76b0",
"md5": "2ae105ffa189f36472ab898e3bb4bc6b",
"sha256": "35c9d0579581ac1e89eed4bc15948cce63ccf46c86200f97549ee87bfc4b9e16"
},
"downloads": -1,
"filename": "jetson_examples-0.0.7-py3-none-any.whl",
"has_sig": false,
"md5_digest": "2ae105ffa189f36472ab898e3bb4bc6b",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 14929,
"upload_time": "2024-04-19T06:18:33",
"upload_time_iso_8601": "2024-04-19T06:18:33.745022Z",
"url": "https://files.pythonhosted.org/packages/0b/95/0a0a9bdadaf6f6011c690d24d633bcb9dca387dc0e6bbdb4654a087d76b0/jetson_examples-0.0.7-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "b6eb5255986dfbc0aca8fce9dcff44a32114d41f710111dcfb9e10e1d4436a69",
"md5": "f04a17db3ece02c0b07ac5085a6c0170",
"sha256": "da4b44f3f3abe24e46a16e43013734f8c4522d36affdffd02416734d270fd729"
},
"downloads": -1,
"filename": "jetson_examples-0.0.7.tar.gz",
"has_sig": false,
"md5_digest": "f04a17db3ece02c0b07ac5085a6c0170",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 11080,
"upload_time": "2024-04-19T06:18:35",
"upload_time_iso_8601": "2024-04-19T06:18:35.606264Z",
"url": "https://files.pythonhosted.org/packages/b6/eb/5255986dfbc0aca8fce9dcff44a32114d41f710111dcfb9e10e1d4436a69/jetson_examples-0.0.7.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-04-19 06:18:35",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "Seeed-Projects",
"github_project": "jetson-examples",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "jetson-examples"
}