- Notifications
You must be signed in to change notification settings - Fork0
KenanGain/SmolLM
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
Here’s the updated README with the additional features:
Welcome to theLLM Models repository! This project demonstrates how to run variousLarge Language Models (LLMs) locally using Ollama, integrated with aNext.js app for an easy-to-use interface. The app supports multiple LLMs and includes advanced features likeVercel AI SDK,streaming text,Next.js themes, andshadcn UI components.
The models you can run include, but are not limited to:
- SmolLM Series: 135M, 360M, 1.7B parameters
- TinyLLaMA: Latest and 1.1B versions
- LLaVA-LLaMA3: 8B parameters
- Qwen Series: 0.5B, 1.5B, 7B parameters
- Mistral-Nemo: Latest
- CodeGemma: Latest and other variations
- Aya, Mixtral, and more
You can explore a wide variety of models, such as:
tinyllama:1.1b, llava-llama3:8b, qwen:0.5b, qwen2:7b, smollm:1.7b, llama3.1, gemma2, mixtral, mistral-nemo, and more.
- Local LLM Inference: Run various LLMs locally usingOllama for efficient inference.
- Vercel AI SDK: Integrated for advanced AI features and optimization.
- Streaming Text: Real-time streaming text output for dynamic interactions.
- Next.js Themes: Dark/light mode toggle usingNext Themes.
- shadcn UI Components: Beautiful, customizable UI components for an enhanced user experience.
- Multiple Models: Choose from small, medium, and large models based on your hardware and requirements.
To run this project, you need the following tools installed:
- Node.js (v14+)
- Ollama
- Next.js
Clone the repository:
git clone https://github.com/KenanGain/SmolLM.gitcd SmolLM
Install dependencies:
npm install
Run the development server:
npm run dev
Open your browser and navigate to
http://localhost:3000
to interact with the models.
You can download any of the supported models locally via Ollama:
ollama pull tinyllama:latestollama pull qwen2:7bollama pull smollm:135M
Adjust the model name based on your specific needs.
├── public# Static assets├── src# Source files│ ├── components# UI Components│ ├── pages# Next.js pages│ └── utils# Utility functions for model inference├── package.json# Dependencies and scripts└── README.md# Project documentation
To run a specific model, simply select the model from the dropdown menu in the app and enter a prompt. The app will display the model's output after processing. Thestreaming text feature provides real-time output, improving user interaction.
The supported LLM models provide flexibility in balancing computational resource use and performance:
- TinyLLaMA: Lightweight tasks with minimal resource usage.
- SmolLM Series: Efficient for reasoning and common sense tasks.
- LLaVA-LLaMA3: Best for complex tasks with a larger memory footprint.
- Next.js: For building the front-end app.
- Ollama: For running the LLM models locally.
- Vercel AI SDK: To integrate advanced AI functionality.
- Streaming Text: For real-time, dynamic text output.
- Next Themes: For dark/light mode support.
- shadcn UI: For beautiful and responsive UI components.
- JavaScript/TypeScript: For scripting and model integration.
- Tailwind CSS: For styling the app interface.
Contributions are welcome! Feel free to fork this repository, submit issues, or create pull requests.
This project is licensed under the MIT License - see theLICENSE file for details.
For any inquiries, you can reach me atkenangain2910@gmail.com.
Let me know if you'd like to add or modify anything!
About
This project runs the SmolLM-135M, SmolLM-360M, and SmolLM-1.7B language models locally using Ollama, integrated with a Next.js app for efficient interaction.
Resources
Uh oh!
There was an error while loading.Please reload this page.
Stars
Watchers
Forks
Releases
Packages0
Uh oh!
There was an error while loading.Please reload this page.