Instructions to use Morphkite/Flowzup-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Morphkite/Flowzup-1 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 Morphkite/Flowzup-1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Morphkite/Flowzup-1:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Morphkite/Flowzup-1:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Morphkite/Flowzup-1:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf Morphkite/Flowzup-1:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf Morphkite/Flowzup-1:Q4_K_M

Use Docker

docker model run hf.co/Morphkite/Flowzup-1:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use Morphkite/Flowzup-1 with Ollama:
```
ollama run hf.co/Morphkite/Flowzup-1:Q4_K_M
```
Unsloth Desktop

How to use Morphkite/Flowzup-1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Morphkite/Flowzup-1:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Morphkite/Flowzup-1:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Morphkite/Flowzup-1 with Docker Model Runner:
```
docker model run hf.co/Morphkite/Flowzup-1:Q4_K_M
```

Lemonade

How to use Morphkite/Flowzup-1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Morphkite/Flowzup-1:Q4_K_M

Run and chat with the model

lemonade run user.Flowzup-1-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Morphkite/Flowzup-1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Morphkite/Flowzup-1: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 Morphkite/Flowzup-1:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Morphkite/Flowzup-1 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Morphkite/Flowzup-1:Q4_K_M

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 "Morphkite/Flowzup-1:Q4_K_M" \
  --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"

Morphkite commited on 4 days ago

Commit

9150dfc

verified ·

1 Parent(s): 5eab778

Upload flowzup.sh with huggingface_hub

Browse files

Files changed (1) hide show

flowzup.sh +33 -0

flowzup.sh ADDED Viewed

	@@ -0,0 +1,33 @@

+#!/usr/bin/env bash
+# Flowzup 1 - SEA-LION v4.5 E2B (Q4_K_M) yang di-rebrand, jalan lokal via llama.cpp
+# Pakai:
+#   ./flowzup.sh chat "pertanyaan kamu"     -> sekali tanya-jawab
+#   ./flowzup.sh server                     -> API server di http://127.0.0.1:8080 (OpenAI-compatible)
+set -euo pipefail
+DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+BIN="$HOME/workspace/tools/llama.cpp/build/bin"
+MODEL="$DIR/Flowzup-1-Q4_K_M.gguf"
+SYS="$DIR/flowzup-system.txt"
+case "${1:-chat}" in
+  chat)
+    "$BIN/llama-cli" -m "$MODEL" -t 4 -c 4096 -n 512 \
+      --temp 0.7 --top-p 0.8 --top-k 20 --single-turn --simple-io \
+      --reasoning off \
+      --system-prompt-file "$SYS" \
+      -p "${2:?tulis pertanyaannya, contoh: ./flowzup.sh chat \"halo, siapa kamu?\"}"
+    ;;
+  server)
+    # Catatan: llama-server tidak punya flag system prompt global.
+    # Aplikasi yang memanggil API harus mengirim isi flowzup-system.txt
+    # sebagai pesan "system" di setiap request chat.
+    "$BIN/llama-server" -m "$MODEL" -t 4 -c 4096 -np 2 \
+      --reasoning off \
+      --host 127.0.0.1 --port 8080 \
+      --alias Flowzup-1
+    ;;
+  *)
+    echo "Perintah tidak dikenal: $1 (pakai: chat | server)" >&2
+    exit 1
+    ;;
+esac