Instructions to use hotdogs/frankenmoe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use hotdogs/frankenmoe 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 hotdogs/frankenmoe:Q4_K_M # Run inference directly in the terminal: llama cli -hf hotdogs/frankenmoe:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf hotdogs/frankenmoe:Q4_K_M # Run inference directly in the terminal: llama cli -hf hotdogs/frankenmoe: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 hotdogs/frankenmoe:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf hotdogs/frankenmoe: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 hotdogs/frankenmoe:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf hotdogs/frankenmoe:Q4_K_M
Use Docker
docker model run hf.co/hotdogs/frankenmoe:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use hotdogs/frankenmoe with Ollama:
ollama run hf.co/hotdogs/frankenmoe:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use hotdogs/frankenmoe with Docker Model Runner:
docker model run hf.co/hotdogs/frankenmoe:Q4_K_M
- Lemonade
How to use hotdogs/frankenmoe with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull hotdogs/frankenmoe:Q4_K_M
Run and chat with the model
lemonade run user.frankenmoe-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Download simple_router.sh from hotdogs/frankenmoe: direct link, hf CLI and curl.
- Browser
- Download file 3.25 kB
-
https://huggingface.co/hotdogs/frankenmoe/resolve/main/simple_router.sh
- Command line
-
hf download hf://hotdogs/frankenmoe/simple_router.sh
-
curl -L -o simple_router.sh https://huggingface.co/hotdogs/frankenmoe/resolve/main/simple_router.sh
3.25 kB
| # ============================================================================= | |
| # Simple Router β llama.cpp wrapper | |
| # Uses 3 GGUF experts + keyword classifier β picks the right one | |
| # | |
| # Usage: | |
| # ./simple_router.sh "Write a Python function to sort a list" | |
| # ./simple_router.sh "Solve x^2 + 5x + 6 = 0" | |
| # ./simple_router.sh "What is the capital of Thailand?" | |
| # | |
| # Requirements: | |
| # - llama.cpp (llama-cli) in PATH | |
| # - GGUF files in ./gguf/{coding,math,chat}/ | |
| # OR set GGUF_CODING, GGUF_MATH, GGUF_CHAT env vars | |
| # ============================================================================= | |
| PROMPT="$*" | |
| if [ -z "$PROMPT" ]; then | |
| echo "Usage: $0 <prompt>" | |
| exit 1 | |
| fi | |
| # βββ GGUF Paths βββ | |
| GGUF_DIR="${GGUF_DIR:-./gguf}" | |
| GGUF_CODING="${GGUF_CODING:-$GGUF_DIR/coding/frankenmoe_coding-Q4_K_M.gguf}" | |
| GGUF_MATH="${GGUF_MATH:-$GGUF_DIR/math/frankenmoe_math-Q4_K_M.gguf}" | |
| GGUF_CHAT="${GGUF_CHAT:-$GGUF_DIR/chat/frankenmoe_chat-Q4_K_M.gguf}" | |
| # βββ Classification βββ | |
| LOWER=$(echo "$PROMPT" | tr '[:upper:]' '[:lower:]') | |
| CODING_KW=("def " "function" "python" "code" "bug" "debug" "api" "import" "class " "algorithm" "implement" "compile" "syntax" "javascript" "html" "css" "sql" "bash" "git" "docker" "write a" "program" "script" "loop" "array" "list" "dict") | |
| MATH_KW=("solve" "equation" "derivative" "integral" "matrix" "eigen" "theorem" "proof" "sqrt" "log" "sin" "cos" "tan" "sum" "probability" "statistic" "graph" "vector" "polynomial" "x =" "x=" "y =" "calculate" "compute" "find the") | |
| CODING_SCORE=0 | |
| MATH_SCORE=0 | |
| for kw in "${CODING_KW[@]}"; do | |
| if [[ "$LOWER" == *"$kw"* ]]; then | |
| ((CODING_SCORE++)) | |
| fi | |
| done | |
| for kw in "${MATH_KW[@]}"; do | |
| if [[ "$LOWER" == *"$kw"* ]]; then | |
| ((MATH_SCORE++)) | |
| fi | |
| done | |
| # βββ Route βββ | |
| if [ "$CODING_SCORE" -gt 0 ] && [ "$CODING_SCORE" -ge "$MATH_SCORE" ]; then | |
| MODEL="$GGUF_CODING" | |
| DOMAIN="π₯οΈ CODING" | |
| elif [ "$MATH_SCORE" -gt 0 ]; then | |
| MODEL="$GGUF_MATH" | |
| DOMAIN="π MATH" | |
| else | |
| MODEL="$GGUF_CHAT" | |
| DOMAIN="π¬ CHAT" | |
| fi | |
| echo "ββββββββββββββββββββββββββββββββββββ" | |
| echo " Simple Router β Domain Router" | |
| echo " Prompt: ${PROMPT:0:60}..." | |
| echo " Route: $DOMAIN" | |
| echo " Model: $(basename "$MODEL")" | |
| echo "ββββββββββββββββββββββββββββββββββββ" | |
| echo "" | |
| # βββ Check model exists βββ | |
| if [ ! -f "$MODEL" ]; then | |
| echo "β Model not found: $MODEL" | |
| echo "" | |
| echo "Download GGUF models:" | |
| echo " wget https://huggingface.co/hotdogs/frankenmoe/resolve/main/coding/frankenmoe_coding-Q4_K_M.gguf" | |
| echo " wget https://huggingface.co/hotdogs/frankenmoe/resolve/main/math/frankenmoe_math-Q4_K_M.gguf" | |
| echo " wget https://huggingface.co/hotdogs/frankenmoe/resolve/main/chat/frankenmoe_chat-Q4_K_M.gguf" | |
| exit 1 | |
| fi | |
| # βββ Run llama.cpp βββ | |
| llama-cli \ | |
| -m "$MODEL" \ | |
| -p "$PROMPT" \ | |
| -n 256 \ | |
| --temp 0.7 \ | |
| --top-p 0.9 \ | |
| --no-display-prompt \ | |
| 2>/dev/null | |
| echo "" | |
| echo "ββββββββββββββββββββββββββββββββββββ" | |