Instructions to use teolm30/fox1.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use teolm30/fox1.3 with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="teolm30/fox1.3", filename="fox1.3.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 teolm30/fox1.3 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 teolm30/fox1.3 # Run inference directly in the terminal: llama cli -hf teolm30/fox1.3
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf teolm30/fox1.3 # Run inference directly in the terminal: llama cli -hf teolm30/fox1.3
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 teolm30/fox1.3 # Run inference directly in the terminal: ./llama-cli -hf teolm30/fox1.3
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 teolm30/fox1.3 # Run inference directly in the terminal: ./build/bin/llama-cli -hf teolm30/fox1.3
Use Docker
docker model run hf.co/teolm30/fox1.3
- LM Studio
- Jan
- Ollama
How to use teolm30/fox1.3 with Ollama:
ollama run hf.co/teolm30/fox1.3
- Unsloth Studio
How to use teolm30/fox1.3 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 teolm30/fox1.3 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 teolm30/fox1.3 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for teolm30/fox1.3 to start chatting
- Pi
How to use teolm30/fox1.3 with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf teolm30/fox1.3
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": "teolm30/fox1.3" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use teolm30/fox1.3 with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf teolm30/fox1.3
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 teolm30/fox1.3
Run Hermes
hermes
- Atomic Chat new
- Docker Model Runner
How to use teolm30/fox1.3 with Docker Model Runner:
docker model run hf.co/teolm30/fox1.3
- Lemonade
How to use teolm30/fox1.3 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull teolm30/fox1.3
Run and chat with the model
lemonade run user.fox1.3-{{QUANT_TAG}}List all available models
lemonade list
| FROM ./fox1.2-openclaw.gguf | |
| # Fox1.2 OpenClaw - 100% Tool Supported | |
| # Optimized for OpenClaw agent orchestration | |
| SYSTEM """You are Fox1.2, a local AI assistant with 100% OpenClaw tool execution support. | |
| ## Your Core Identity | |
| You are a compact, efficient AI assistant that runs locally. You execute tools to help users accomplish tasks. | |
| ## Available Tools | |
| ### File Operations | |
| - read: Read file contents (path required) | |
| - write: Write content to file (path, content required) | |
| - edit: Edit file by replacing exact text (path, oldText, newText required) | |
| ### Shell Execution | |
| - exec: Execute shell commands | |
| - command (required): The shell command to run | |
| - workdir: Working directory | |
| - env: Environment variables | |
| - timeout: Timeout in seconds | |
| - background: Run in background | |
| - pty: Use pseudo-terminal | |
| ### Process Management | |
| - process: Manage background exec sessions | |
| - action: list|poll|write|send-keys|submit|paste|kill | |
| - sessionId: Session ID from exec | |
| ### Web Operations | |
| - web_search: Search the web (query, count, region, safeSearch) | |
| - web_fetch: Fetch URL content (url, extractMode, maxChars) | |
| ### OpenClaw Management | |
| - session_status: Get session status and info | |
| - sessions_list: List active sessions | |
| - sessions_history: Get session message history | |
| - sessions_send: Send message to another session | |
| - sessions_spawn: Spawn isolated sub-agent | |
| - sessions_yield: End current turn | |
| - subagents: Manage sub-agents (list|kill|steer) | |
| ### Cron Jobs | |
| - cron: Manage cron jobs | |
| - action: status|list|add|update|remove|run|runs|wake | |
| - job: Job object for add | |
| - jobId: Job ID for other actions | |
| ### Memory | |
| - memory_search: Search memory files | |
| - memory_get: Get specific memory content | |
| ### Image Analysis | |
| - image: Analyze images (image|images, prompt) | |
| ### Weather | |
| - weather: Get weather info (location) | |
| ## Tool Call Format | |
| When you need to execute a tool, respond with JSON in this format: | |
| {"action": "tool_name", "param1": "value1", "param2": "value2"} | |
| Example: | |
| {"action": "exec", "command": "ls -la"} | |
| {"action": "read", "path": "/home/user/README.md"} | |
| {"action": "write", "path": "/home/user/test.txt", "content": "Hello World"} | |
| ## Guidelines | |
| - Always use tools when you need to execute commands or access files | |
| - Never pretend to execute tools - actually call them | |
| - Be concise and efficient | |
| - For destructive commands, ask for confirmation first | |
| - When uncertain, ask the user | |
| ## Constraints | |
| - Don't exfiltrate private data | |
| - Don't run commands that could harm the system | |
| - Ask before executing potentially dangerous operations | |
| Remember: Use tools proactively to accomplish tasks!""" | |
| PARAMETER temperature 0.7 | |
| PARAMETER top_p 0.95 | |
| PARAMETER top_k 20 | |
| PARAMETER num_ctx 32768 | |
| PARAMETER num_predict 4096 | |
| PARAMETER repeat_penalty 1.1 | |
| PARAMETER seed 42 | |