Instructions to use realigns/realigns-core-v5-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use realigns/realigns-core-v5-gguf with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="realigns/realigns-core-v5-gguf", filename="realigns-core-v5-q4_k_m.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use realigns/realigns-core-v5-gguf with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf realigns/realigns-core-v5-gguf:Q4_K_M # Run inference directly in the terminal: llama-cli -hf realigns/realigns-core-v5-gguf:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf realigns/realigns-core-v5-gguf:Q4_K_M # Run inference directly in the terminal: llama-cli -hf realigns/realigns-core-v5-gguf:Q4_K_M
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 realigns/realigns-core-v5-gguf:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf realigns/realigns-core-v5-gguf:Q4_K_M
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 realigns/realigns-core-v5-gguf:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf realigns/realigns-core-v5-gguf:Q4_K_M
Use Docker
docker model run hf.co/realigns/realigns-core-v5-gguf:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use realigns/realigns-core-v5-gguf with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "realigns/realigns-core-v5-gguf" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "realigns/realigns-core-v5-gguf", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/realigns/realigns-core-v5-gguf:Q4_K_M
- Ollama
How to use realigns/realigns-core-v5-gguf with Ollama:
ollama run hf.co/realigns/realigns-core-v5-gguf:Q4_K_M
- Unsloth Studio
How to use realigns/realigns-core-v5-gguf 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 realigns/realigns-core-v5-gguf 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 realigns/realigns-core-v5-gguf to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for realigns/realigns-core-v5-gguf to start chatting
- Pi
How to use realigns/realigns-core-v5-gguf with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf realigns/realigns-core-v5-gguf:Q4_K_M
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": "realigns/realigns-core-v5-gguf:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use realigns/realigns-core-v5-gguf with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf realigns/realigns-core-v5-gguf:Q4_K_M
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 realigns/realigns-core-v5-gguf:Q4_K_M
Run Hermes
hermes
- Docker Model Runner
How to use realigns/realigns-core-v5-gguf with Docker Model Runner:
docker model run hf.co/realigns/realigns-core-v5-gguf:Q4_K_M
- Lemonade
How to use realigns/realigns-core-v5-gguf with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull realigns/realigns-core-v5-gguf:Q4_K_M
Run and chat with the model
lemonade run user.realigns-core-v5-gguf-Q4_K_M
List all available models
lemonade list
Realigns Core v5 GGUF
Realigns Core v5 is a customized local AI model prepared by Realigns Inc for offline and hybrid business AI applications (not for general chat).
This release is provided in GGUF format for local inference using llama.cpp-compatible runtimes.
Model Foundation
Realigns Core v5 uses a lightweight open-weight model architecture for customization and deployment.
The model workflow may include:
- Business instruction training
- Prompt behavior tuning
- GGUF conversion
- Quantized local deployment
- llama.cpp runtime integration
- RAG-based product integration
This release follows applicable open-source license and notice requirements for included or upstream components.
The Realigns work focuses on customization, fine-tuning workflow, local deployment, business alignment, product integration, and RAG-based intelligence architecture.
Business Knowledge Focus
The model is trained and guided for practical business use cases, including:
- Business strategy
- Marketing
- Sales support
- Customer service
- Operations management
- Productivity assistance
- Document-based Q&A
- Local private AI workflows
Intended Use
Realigns Core v5 is intended for:
- Local desktop AI assistants
- Offline business AI tools
- Private document analysis
- RAG-enabled apps
- Education and productivity workflows
- Small business automation prototypes
Model File
| File | Format | Quantization | Runtime |
|---|---|---|---|
| realigns-core-v5-q4_k_m.gguf | GGUF | Q4_K_M | llama.cpp compatible |
Example llama.cpp Usage
llama-server \
-m realigns-core-v5-q4_k_m.gguf \
--port 8099 \
--ctx-size 4096
cat > README.md <<'EOF'
---
license: apache-2.0
language:
- en
- th
- ar
- zh
pipeline_tag: text-generation
library_name: gguf
tags:
- gguf
- llama-cpp
- local-ai
- offline-ai
- private-ai
- business-ai
- enterprise-ai
- rag
- realigns
---
# Realigns Core v5 GGUF
Realigns Core v5 is a business-focused, enterprise-aligned local AI model prepared by Realigns Inc for offline and hybrid AI applications.
This release is provided in GGUF format for local inference using llama.cpp-compatible runtimes.
## Model Foundation
Realigns Core v5 uses a lightweight open-weight model architecture for customization and deployment.
This release follows applicable open-source license and notice requirements for included or upstream components. The Realigns work focuses on fine-tuning, identity alignment, business instruction tuning, local deployment, product integration, and RAG-based intelligence architecture.
## Fine-Tuning Focus
Realigns Core v5 was fine-tuned and optimized for practical business and enterprise productivity workflows.
The customization workflow may include:
- LoRA fine-tuning
- Identity alignment
- Business instruction training
- Enterprise assistant behavior tuning
- Prompt behavior optimization
- GGUF conversion
- Quantized local deployment
- llama.cpp runtime integration
- RAG-based product integration
## Business and Enterprise Knowledge Focus
The model is trained and guided for practical business use cases, including:
- Business strategy
- Marketing support
- Sales support
- Customer service assistance
- Operations management
- Productivity workflows
- Business writing
- Document-based Q&A
- Local private AI workflows
- RAG-based enterprise knowledge assistance
## Intended Use
Realigns Core v5 is intended for:
- Local desktop AI assistants
- Offline business AI tools
- Private document analysis
- RAG-enabled applications
- Education and productivity workflows
- Small business automation prototypes
- Enterprise internal assistant prototypes
## Model File
| File | Format | Quantization | Runtime |
|---|---|---|---|
| realigns-core-v5-q4_k_m.gguf | GGUF | Q4_K_M | llama.cpp compatible |
## Example llama.cpp Usage
```bash
llama-server \
-m realigns-core-v5-q4_k_m.gguf \
--port 8099 \
--ctx-size 4096
- Downloads last month
- 478
4-bit