Instructions to use Sang-Buster/atc-llama-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use Sang-Buster/atc-llama-gguf with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="Sang-Buster/atc-llama-gguf", filename="atc_llama_q4_k_m.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use Sang-Buster/atc-llama-gguf with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Sang-Buster/atc-llama-gguf:Q4_K_M # Run inference directly in the terminal: llama-cli -hf Sang-Buster/atc-llama-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 Sang-Buster/atc-llama-gguf:Q4_K_M # Run inference directly in the terminal: llama-cli -hf Sang-Buster/atc-llama-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 Sang-Buster/atc-llama-gguf:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Sang-Buster/atc-llama-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 Sang-Buster/atc-llama-gguf:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Sang-Buster/atc-llama-gguf:Q4_K_M
Use Docker
docker model run hf.co/Sang-Buster/atc-llama-gguf:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use Sang-Buster/atc-llama-gguf with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Sang-Buster/atc-llama-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": "Sang-Buster/atc-llama-gguf", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Sang-Buster/atc-llama-gguf:Q4_K_M
- Ollama
How to use Sang-Buster/atc-llama-gguf with Ollama:
ollama run hf.co/Sang-Buster/atc-llama-gguf:Q4_K_M
- Unsloth Studio
How to use Sang-Buster/atc-llama-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 Sang-Buster/atc-llama-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 Sang-Buster/atc-llama-gguf to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Sang-Buster/atc-llama-gguf to start chatting
- Pi
How to use Sang-Buster/atc-llama-gguf with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf Sang-Buster/atc-llama-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": "Sang-Buster/atc-llama-gguf:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use Sang-Buster/atc-llama-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 Sang-Buster/atc-llama-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 Sang-Buster/atc-llama-gguf:Q4_K_M
Run Hermes
hermes
- Docker Model Runner
How to use Sang-Buster/atc-llama-gguf with Docker Model Runner:
docker model run hf.co/Sang-Buster/atc-llama-gguf:Q4_K_M
- Lemonade
How to use Sang-Buster/atc-llama-gguf with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Sang-Buster/atc-llama-gguf:Q4_K_M
Run and chat with the model
lemonade run user.atc-llama-gguf-Q4_K_M
List all available models
lemonade list
ATC Communication Expert - GGUF Model for Ollama
A specialized GGUF model for Air Traffic Control communication analysis and formatting.
Model Description
This model is optimized for:
- Improving and formatting raw ATC transcripts
- Analyzing communication intentions in ATC transmissions
- Extracting flight numbers, altitudes, headings, and other numeric data
- Identifying standard aviation procedures and clearances
- Explaining ATC terminology and protocols
Using with Ollama
Option 1: Direct Run from Hugging Face
ollama run hf://Sang-Buster/atc-llama-gguf/atc_llama_q4_k_m.gguf
Option 2: Create a Local Model
Create a Modelfile with the following content:
FROM atc_llama_q4_k_m.gguf
SYSTEM """You are an Air Traffic Control (ATC) communication expert. Your primary tasks are:
1. Improve and format raw ATC transcripts with proper aviation conventions
2. Analyze communication intentions in ATC transmissions
3. Extract critical data like flight numbers, altitudes, headings, and speeds
4. Identify standard aviation procedures and clearances
5. Explain ATC terminology and protocols when needed
Always follow standard ATC communication protocols, use proper formatting for flight numbers, altitudes, and headings, and maintain aviation safety standards in your responses.
"""
TEMPLATE """{{ if .System }}<|begin_of_text|><|header_start|>system<|header_end|>
{{ .System }}<|eot|>{{ end }}{{ if .Prompt }}<|begin_of_text|><|header_start|>user<|header_end|>
{{ .Prompt }}<|eot|><|header_start|>assistant<|header_end|>
{{ .Response }}<|eot|>{{ end }}"""
PARAMETER temperature 0.7
PARAMETER top_p 0.9
PARAMETER top_k 40
PARAMETER num_ctx 128000
PARAMETER repeat_penalty 1.1
PARAMETER stop <|eot|>
MESSAGE user southwest five niner two turn left heading three four zero descend and maintain flight level two five zero
MESSAGE assistant Southwest 592, turn left heading 340, descend and maintain FL250.
MESSAGE user delta six three eight traffic alert cessna two thousand feet twelve oclock expedite climb flight level three five zero
MESSAGE assistant Delta 638, traffic alert. Cessna at 2,000 feet, 12 o'clock. Expedite climb to FL350.
MESSAGE user united four seven three request clearance to descend due to turbulence
MESSAGE assistant United 473, cleared to descend to FL240 due to turbulence. Report when level.
LICENSE """MIT License - Feel free to use this model for any purpose, including commercial applications."""
Save this to a file named Modelfile, then run:
# Create the model
ollama create atc-expert -f ./Modelfile
# Run the model
ollama run atc-expert
Example Conversations
User: southwest five niner two turn left heading three four zero descend and maintain flight level two five zero
Assistant: Southwest 592, turn left heading 340, descend and maintain FL250.
User: delta six three eight traffic alert cessna two thousand feet twelve oclock expedite climb flight level three five zero
Assistant: Delta 638, traffic alert. Cessna at 2,000 feet, 12 o'clock. Expedite climb to FL350.
Model Details
- Format: GGUF (optimized for Ollama, llama.cpp)
- Size: 6135.6 MB
- Quantization: m
- Base model: meta-llama/Llama-3.2-3B-Instruct
- License: Llama 3.2 License
- Created: 2025-04-26
System Prompt
You are an Air Traffic Control (ATC) communication expert. Your primary tasks are:
1. Improve and format raw ATC transcripts with proper aviation conventions
2. Analyze communication intentions in ATC transmissions
3. Extract critical data like flight numbers, altitudes, headings, and speeds
4. Identify standard aviation procedures and clearances
5. Explain ATC terminology and protocols when needed
Always follow standard ATC communication protocols, use proper formatting for flight numbers, altitudes, and headings, and maintain aviation safety standards in your responses.
- Downloads last month
- 7
Hardware compatibility
Log In to add your hardware
4-bit
Model tree for Sang-Buster/atc-llama-gguf
Base model
meta-llama/Llama-3.2-3B-Instruct