Instructions to use telivity/haip-ai with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use telivity/haip-ai with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="telivity/haip-ai",
	filename="haip-ai.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 telivity/haip-ai 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 telivity/haip-ai
# Run inference directly in the terminal:
llama cli -hf telivity/haip-ai

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf telivity/haip-ai
# Run inference directly in the terminal:
llama cli -hf telivity/haip-ai

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 telivity/haip-ai
# Run inference directly in the terminal:
./llama-cli -hf telivity/haip-ai

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 telivity/haip-ai
# Run inference directly in the terminal:
./build/bin/llama-cli -hf telivity/haip-ai

Use Docker

docker model run hf.co/telivity/haip-ai

LM Studio
Jan
Ollama
How to use telivity/haip-ai with Ollama:
```
ollama run hf.co/telivity/haip-ai
```

Unsloth Studio

How to use telivity/haip-ai 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 telivity/haip-ai 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 telivity/haip-ai to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for telivity/haip-ai to start chatting

How to use telivity/haip-ai with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf telivity/haip-ai

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": "telivity/haip-ai"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use telivity/haip-ai with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf telivity/haip-ai

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 telivity/haip-ai

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use telivity/haip-ai with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf telivity/haip-ai

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 "telivity/haip-ai" \
  --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"

Docker Model Runner
How to use telivity/haip-ai with Docker Model Runner:
```
docker model run hf.co/telivity/haip-ai
```

Lemonade

How to use telivity/haip-ai with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull telivity/haip-ai

Run and chat with the model

lemonade run user.haip-ai-{{QUANT_TAG}}

List all available models

lemonade list

HAIP AI

haip-ai is the optional local model for HAIP (Hotel AI Platform). It produces compact, grounded explanations of HAIP's deterministic agent decisions — it never executes actions and only reasons over the numbers the agents already computed.

Runs locally via Ollama (GGUF, Q4_K_M)
Output is strict JSON: {"rationale": string, "suggestions": string[]}
Held-out quality: 100% JSON-valid, 88.8% grounded (via the exact runtime contract)

Output contract

system: You are HAIP AI, a hotel revenue & operations analyst. ... Respond ONLY with compact
        JSON: {"rationale": string (<=60 words), "suggestions": string[] (0-3 short items)}.
user:   Agent: {agentType}\nDecision: {decisionType}\nNumbers:\n{json}
assistant: {"rationale": "...", "suggestions": ["..."]}

Use with Ollama

# while this repo is private, configure your HF token first
ollama pull hf.co/telivity/haip-ai

# or download haip-ai.gguf + Modelfile, then:
ollama create haip-ai -f Modelfile

Enable in HAIP: HAIP_AI_ENABLED=true HAIP_AI_MODEL=haip-ai (opt-in — the PMS works fully without it).

Attribution

See THIRD_PARTY_LICENSES in the HAIP repo for upstream model attribution and their license terms.

Downloads last month: 9

GGUF

Model size

8B params

Architecture

gemma4

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