Instructions to use PyThaGo/LLMLit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use PyThaGo/LLMLit with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="PyThaGo/LLMLit", filename="LLMLit-0.2-8B-Instruct.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use PyThaGo/LLMLit with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf PyThaGo/LLMLit # Run inference directly in the terminal: llama cli -hf PyThaGo/LLMLit
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf PyThaGo/LLMLit # Run inference directly in the terminal: llama cli -hf PyThaGo/LLMLit
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf PyThaGo/LLMLit # Run inference directly in the terminal: ./llama-cli -hf PyThaGo/LLMLit
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf PyThaGo/LLMLit # Run inference directly in the terminal: ./build/bin/llama-cli -hf PyThaGo/LLMLit
Use Docker
docker model run hf.co/PyThaGo/LLMLit
- LM Studio
- Jan
- Ollama
How to use PyThaGo/LLMLit with Ollama:
ollama run hf.co/PyThaGo/LLMLit
- Unsloth Studio
How to use PyThaGo/LLMLit with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for PyThaGo/LLMLit to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for PyThaGo/LLMLit to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for PyThaGo/LLMLit to start chatting
- Pi
How to use PyThaGo/LLMLit with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf PyThaGo/LLMLit
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "PyThaGo/LLMLit" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use PyThaGo/LLMLit with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf PyThaGo/LLMLit
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default PyThaGo/LLMLit
Run Hermes
hermes
- Atomic Chat new
- OpenClaw new
How to use PyThaGo/LLMLit with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf PyThaGo/LLMLit
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "PyThaGo/LLMLit" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
- Docker Model Runner
How to use PyThaGo/LLMLit with Docker Model Runner:
docker model run hf.co/PyThaGo/LLMLit
- Lemonade
How to use PyThaGo/LLMLit with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull PyThaGo/LLMLit
Run and chat with the model
lemonade run user.LLMLit-{{QUANT_TAG}}List all available models
lemonade list
Cristian Sas commited on
Update README.md
Browse files
README.md
CHANGED
|
@@ -148,6 +148,143 @@ Efforts to interpret the model include:
|
|
| 148 |
## Environmental Impact
|
| 149 |
Training LLMLit resulted in estimated emissions of ~200 kg CO2eq. Carbon offsets were purchased to mitigate environmental impact. Future optimizations aim to reduce energy consumption.
|
| 150 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 151 |

|
| 152 |
|
| 153 |
|
|
|
|
| 148 |
## Environmental Impact
|
| 149 |
Training LLMLit resulted in estimated emissions of ~200 kg CO2eq. Carbon offsets were purchased to mitigate environmental impact. Future optimizations aim to reduce energy consumption.
|
| 150 |
|
| 151 |
+
|
| 152 |
+
|
| 153 |
+
LLMLit β The Cutting-Edge AI Assistant for Performance Analysis and Prediction
|
| 154 |
+
|
| 155 |
+
LLMLIT β Coming Soon
|
| 156 |
+
The premium version of the LLama 3 model, LLMLIT, sets a new standard in AI through advanced customization and innovative technologies, offering ideal solutions for a wide range of industries and applications.
|
| 157 |
+
|
| 158 |
+
This version integrates Retrieval-Augmented Generation (RAG) capabilities, ensuring fast and accurate access to relevant and specialized information.
|
| 159 |
+
|
| 160 |
+
Key Features of LLMLIT:
|
| 161 |
+
|
| 162 |
+
Advanced Customization: Tailored to meet the specific needs of each user, delivering optimized solutions.
|
| 163 |
+
|
| 164 |
+
Enhanced RAG Integration: Support for multiple domains and complex data sources.
|
| 165 |
+
|
| 166 |
+
Innovative Frontend and Backend:Frontend: Intuitive, customizable interfaces with user-centric interactions.
|
| 167 |
+
|
| 168 |
+
Backend: Top-tier performance, rapid data processing, and efficient task management.
|
| 169 |
+
|
| 170 |
+
Extensive Community Integrations
|
| 171 |
+
LLMLIT supports a wide range of platforms and applications, offering unparalleled flexibility:
|
| 172 |
+
|
| 173 |
+
Web & Desktop: Open WebUI, HTML UI, Ollama GUI, LMstudio, MindMac, Ollama Spring.
|
| 174 |
+
|
| 175 |
+
Mobile: Native apps such as Enchanted, macAI, Ollama Telegram Bot, and Ollama RAG Chatbot.
|
| 176 |
+
|
| 177 |
+
CLI & Terminal: Advanced plugins for Emacs, Vim, and tools like ShellOracle and typechat-cli.
|
| 178 |
+
|
| 179 |
+
Extensions & Plugins: Raycast Extensions, Obsidian Plugins, Ollama for Discord, and more.
|
| 180 |
+
|
| 181 |
+
Package Managers: Integration with Pacman, Gentoo, Nix, and Flox.
|
| 182 |
+
|
| 183 |
+
Enterprise Solutions & Advanced AI
|
| 184 |
+
|
| 185 |
+
AI Frameworks and Chatbot UI: Hollama, Saddle, big-AGI, Cheshire Cat, Amica.
|
| 186 |
+
|
| 187 |
+
Backend RAG Integration: LangChain, LangChainGo, Haystack, and Semantic Kernel.
|
| 188 |
+
|
| 189 |
+
Developer Support: VSCode extensions, QodeAssist for Qt Creator, and Ollama support for multiple programming languages (Java, Python, C++, etc.).
|
| 190 |
+
|
| 191 |
+
Team and Multi-Agent Applications: AnythingLLM, crewAI, and BrainSoup.
|
| 192 |
+
|
| 193 |
+
Cross-Platform Performance
|
| 194 |
+
LLMLIT delivers advanced interoperability:
|
| 195 |
+
|
| 196 |
+
MacOS Native: OllamaSwift, macAI, and support for Apple Vision Pro.
|
| 197 |
+
|
| 198 |
+
Windows/Linux: Docker-native and containerized apps like ARGO and StreamDeploy.
|
| 199 |
+
|
| 200 |
+
Mobile Applications: Ollama Telegram Bot, Ollama Discord Bot, and Ollama RAG Chatbot.
|
| 201 |
+
|
| 202 |
+
Open Ecosystem: Integration with popular platforms such as Google Mesop, Firebase, and SAP ABAP.
|
| 203 |
+
|
| 204 |
+
The Future of AI is Here π
|
| 205 |
+
LLMLIT revolutionizes how we work with large language models, offering a scalable, powerful, and adaptable platform ready to meet the most demanding needs with innovation, flexibility, and superior performance.
|
| 206 |
+
|
| 207 |
+
|
| 208 |
+
|
| 209 |
+
π Themes and Agents: Revolutionizing AI-driven Applications
|
| 210 |
+
|
| 211 |
+
The integration of AI-powered technologies into development tools is rapidly transforming how applications are built and deployed. With LLMLit as the core engine, this suite of tools offers groundbreaking possibilities, from low-code app building to advanced conversational agents.
|
| 212 |
+
|
| 213 |
+
AI-Driven Development in Your Terminal π
|
| 214 |
+
|
| 215 |
+
Design full-stack web applications with AI-powered capabilities directly from your terminal. This environment is built for large, real-world tasks, allowing developers to prompt, run, edit, and deploy web apps with seamless integration into your workflow.
|
| 216 |
+
|
| 217 |
+
|
| 218 |
+
|
| 219 |
+
Low-Code App Builder for RAG and Multi-Agent AI Applications π§
|
| 220 |
+
|
| 221 |
+
Python-based and agnostic to any model, API, or database, this platform simplifies the development of complex AI-driven applications, including Retrieval-Augmented Generation (RAG) and multi-agent AI systems.
|
| 222 |
+
|
| 223 |
+
It empowers developers to create powerful apps without needing extensive coding knowledge, making it ideal for businesses and researchers who want to implement sophisticated AI without the overhead.
|
| 224 |
+
|
| 225 |
+
Open Voice OS and HiveMind Installer π
|
| 226 |
+
|
| 227 |
+
Ansible-based: Set up and configure your Open Voice OS and HiveMind installer effortlessly with an intuitive, text-based user interface.
|
| 228 |
+
|
| 229 |
+
This provides an easy installation and setup process, especially designed for voice-enabled applications and environments that rely on multi-agent systems.
|
| 230 |
+
|
| 231 |
+
Generative UI: AI-Powered Search Engine π
|
| 232 |
+
|
| 233 |
+
Harness the power of a generative UI for your search engines. This AI-powered tool offers contextual searches and adaptive results, providing users with an efficient and intelligent way to explore content and data. It can be embedded in various systems like websites or apps to improve user experience.
|
| 234 |
+
|
| 235 |
+
|
| 236 |
+
|
| 237 |
+
π§ LitSeek-R1: Distilled Version
|
| 238 |
+
|
| 239 |
+
A lighter, distilled version of the powerful LLMLit model, LitSeek-R1 maintains the same robust capabilities but with optimized performance for faster, more efficient responses. Perfect for applications requiring speed and low-latency operations.
|
| 240 |
+
|
| 241 |
+
|
| 242 |
+
|
| 243 |
+
Agent and Application Themes
|
| 244 |
+
|
| 245 |
+
π LitAgentWeb-ui
|
| 246 |
+
|
| 247 |
+
Direct Interaction with LLMLit: No complex installations required! This theme allows users to interact with LLMLit through a simple, intuitive web interface, making it ideal for applications that need to be accessed directly from a browser.
|
| 248 |
+
|
| 249 |
+
Whether you're building a customer support system or a virtual assistant, AgentWeb-ui provides a fast and simple experience.
|
| 250 |
+
|
| 251 |
+
π¬ LibreChat
|
| 252 |
+
|
| 253 |
+
Multi-AI Integration: LibreChat is a powerful chatbot that integrates multiple AI models, including LLMLit. It provides a natural conversational experience, whether for customer support or virtual assistance.
|
| 254 |
+
|
| 255 |
+
Its flexibility and scalability make it suitable for a wide range of applications, helping businesses manage automated communication at scale.
|
| 256 |
+
|
| 257 |
+
π₯οΈ LITflow
|
| 258 |
+
|
| 259 |
+
Low-Code Platform for Custom Apps: Langflow is a low-code solution for creating custom applications that integrate seamlessly with LLMLit.
|
| 260 |
+
|
| 261 |
+
It excels in building RAG-based applications, combining search and content generation to deliver smarter, faster solutions for complex environments. It's perfect for anyone looking to integrate advanced AI into their applications without the complexity of traditional development.
|
| 262 |
+
|
| 263 |
+
π± NextChat
|
| 264 |
+
|
| 265 |
+
Cross-Platform Conversational App: NextChat is a fast, easy-to-use application that enables smooth, interactive conversations across different platforms.
|
| 266 |
+
|
| 267 |
+
By integrating LLMLit, NextChat offers a dynamic interactive experience, ideal for users who want to have effective conversations with AI, whether for personal use, business, or service centers.
|
| 268 |
+
|
| 269 |
+
π£οΈ VoiceLit
|
| 270 |
+
|
| 271 |
+
Voice Interaction Capabilities: Extend LLMLitβs abilities into the voice realm with VoiceLit. This extension brings AI-driven voice support to your applications, whether theyβre for personal assistants or service centers.
|
| 272 |
+
|
| 273 |
+
It enhances accessibility and interactivity, making it essential for creating voice-enabled AI applications.
|
| 274 |
+
|
| 275 |
+
π Web-llm-chat
|
| 276 |
+
|
| 277 |
+
Run LLMLit Directly in the Browser: With Web-llm-chat, users can run LLMLit directly in their browser, bypassing the need for servers.
|
| 278 |
+
|
| 279 |
+
This ensures maximum privacy and speed, offering a confidential and fast interaction experience. Itβs perfect for applications where confidentiality and performance are of utmost importance.
|
| 280 |
+
|
| 281 |
+
The Future of AI Interaction ππ‘
|
| 282 |
+
|
| 283 |
+
These themes and agents open up a wide array of possibilities, allowing businesses, developers, and individuals to easily integrate LLMLit into their systems. Whether it's building a simple chatbot or a highly sophisticated voice-enabled app, LLMLit offers the flexibility and power to transform the way we interact with AI technology. π₯
|
| 284 |
+
|
| 285 |
+
|
| 286 |
+
|
| 287 |
+
|
| 288 |

|
| 289 |
|
| 290 |
|