Instructions to use uvaiseo/ibm-ace-expert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use uvaiseo/ibm-ace-expert 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 uvaiseo/ibm-ace-expert
# Run inference directly in the terminal:
llama cli -hf uvaiseo/ibm-ace-expert

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf uvaiseo/ibm-ace-expert
# Run inference directly in the terminal:
llama cli -hf uvaiseo/ibm-ace-expert

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 uvaiseo/ibm-ace-expert
# Run inference directly in the terminal:
./llama-cli -hf uvaiseo/ibm-ace-expert

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 uvaiseo/ibm-ace-expert
# Run inference directly in the terminal:
./build/bin/llama-cli -hf uvaiseo/ibm-ace-expert

Use Docker

docker model run hf.co/uvaiseo/ibm-ace-expert

LM Studio
Jan
Ollama
How to use uvaiseo/ibm-ace-expert with Ollama:
```
ollama run hf.co/uvaiseo/ibm-ace-expert
```
Unsloth Desktop

How to use uvaiseo/ibm-ace-expert with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf uvaiseo/ibm-ace-expert

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": "uvaiseo/ibm-ace-expert"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use uvaiseo/ibm-ace-expert with Docker Model Runner:
```
docker model run hf.co/uvaiseo/ibm-ace-expert
```

Lemonade

How to use uvaiseo/ibm-ace-expert with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull uvaiseo/ibm-ace-expert

Run and chat with the model

lemonade run user.ibm-ace-expert-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use uvaiseo/ibm-ace-expert with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf uvaiseo/ibm-ace-expert

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 uvaiseo/ibm-ace-expert

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use uvaiseo/ibm-ace-expert with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf uvaiseo/ibm-ace-expert

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 "uvaiseo/ibm-ace-expert" \
  --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"

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

IBM ACE Expert LLM

A fine-tuned LLM specialising in IBM App Connect Enterprise (ACE), IBM API Connect, IBM MQ, and IBM DataPower.

How to run locally

Option 1 — Ollama (easiest)

ollama run hf.co/YOUR_USERNAME/ibm-ace-expert

Option 2 — LM Studio

Download the GGUF file and load it in LM Studio.

Training details

Base model: Meta-Llama-3.1-8B-Instruct
Method: LoRA fine-tuning with MLX-LM
Training data: IBM App Connect Enterprise documentation
Dataset: ~10,400 Q&A pairs (Claude API + Ollama generated)
Hardware: Apple M4 Mac (48GB RAM)
Iterations: 2,000
Final val loss: 1.105

Topics covered

IBM App Connect Enterprise (ACE) message flows
BAR file creation and deployment
Integration Server and Integration Node management
ESQL programming
Configurable services and policy projects
Migration from IBM Integration Bus to ACE
IBM MQ queue manager configuration
IBM API Connect API management

Downloads last month: 8

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support