GGUF
conversational
How to use from
llama.cpp
Install from brew
brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TroyDoesAI/Agent-Flow-Phone_Demo_3GB_RAM:Q2_K
# Run inference directly in the terminal:
llama-cli -hf TroyDoesAI/Agent-Flow-Phone_Demo_3GB_RAM:Q2_K
Install from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TroyDoesAI/Agent-Flow-Phone_Demo_3GB_RAM:Q2_K
# Run inference directly in the terminal:
llama-cli -hf TroyDoesAI/Agent-Flow-Phone_Demo_3GB_RAM:Q2_K
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 TroyDoesAI/Agent-Flow-Phone_Demo_3GB_RAM:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf TroyDoesAI/Agent-Flow-Phone_Demo_3GB_RAM:Q2_K
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 TroyDoesAI/Agent-Flow-Phone_Demo_3GB_RAM:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TroyDoesAI/Agent-Flow-Phone_Demo_3GB_RAM:Q2_K
Use Docker
docker model run hf.co/TroyDoesAI/Agent-Flow-Phone_Demo_3GB_RAM:Q2_K
Quick Links

Flowchart Generation Model

Overview

This model generates Mermaid diagrams from a sequence of steps provided in the input. It processes the input text and automatically outputs a flowchart that visually represents the steps. The model strictly follows a defined template and does not require any additional prompt engineering.

How It Works

The model takes a set of sequential instructions as input and produces a flowchart diagram in Mermaid format.

Video Performance On A Mac M1 8GB:

https://x.com/troydoesai/status/1833671273765020158

Input Format

The input is a sequence of steps written as plain text:

Step 1: Do something.
Step 2: Do the next thing.
Step 3: Complete the task.

Output Format

The output is a Mermaid diagram:

graph TD;
   Step1 --> Step2;
   Step2 --> Step3;
   ...

Example

Input:

Fill the coffee maker with water.
Add coffee grounds to the filter.
Turn on the coffee maker.
Wait for brewing to finish.
Pour the coffee.
Optional: Add sugar or milk.
Enjoy your coffee.

Output:

graph TD;
   A[Fill Coffee Maker] --> B[Add Water];
   B --> C[Add Coffee Grounds];
   C --> D[Turn On Coffee Maker];
   D --> E[Wait for Brewing];
   E --> F[Pour Coffee];
   F --> G{Add Sugar & Milk?};
   G--Yes-->H[Mix In];
   H-->I[Enjoy Coffee];
   G--No-->I;

Features

  • Transforms plain text instructions into Mermaid flowcharts. (It might work with code, stories, or anything that has a flow)
  • Follows a consistent input-output template.
  • Simple and direct without requiring additional prompt adjustments.

Use Cases

  • Visualizing step-by-step processes.
  • Converting written instructions into clear, easy-to-read diagrams.
  • Ideal for documentation, workflows, and tutorials.

How To Use With Ollama

  • Please Use Provided Ollama: Modelfile
ollama create AgentFlow
ollama run AgentFlow
Downloads last month
19
GGUF
Model size
4B params
Architecture
llama
Hardware compatibility
Log In to add your hardware

2-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support