Instructions to use ShinyUser/tpn002-step750-e82aa2977506 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use ShinyUser/tpn002-step750-e82aa2977506 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 ShinyUser/tpn002-step750-e82aa2977506
# Run inference directly in the terminal:
llama cli -hf ShinyUser/tpn002-step750-e82aa2977506

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ShinyUser/tpn002-step750-e82aa2977506
# Run inference directly in the terminal:
llama cli -hf ShinyUser/tpn002-step750-e82aa2977506

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 ShinyUser/tpn002-step750-e82aa2977506
# Run inference directly in the terminal:
./llama-cli -hf ShinyUser/tpn002-step750-e82aa2977506

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 ShinyUser/tpn002-step750-e82aa2977506
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ShinyUser/tpn002-step750-e82aa2977506

Use Docker

docker model run hf.co/ShinyUser/tpn002-step750-e82aa2977506

LM Studio
Jan
Ollama
How to use ShinyUser/tpn002-step750-e82aa2977506 with Ollama:
```
ollama run hf.co/ShinyUser/tpn002-step750-e82aa2977506
```
Unsloth Desktop

How to use ShinyUser/tpn002-step750-e82aa2977506 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ShinyUser/tpn002-step750-e82aa2977506

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": "ShinyUser/tpn002-step750-e82aa2977506"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ShinyUser/tpn002-step750-e82aa2977506 with Docker Model Runner:
```
docker model run hf.co/ShinyUser/tpn002-step750-e82aa2977506
```

Lemonade

How to use ShinyUser/tpn002-step750-e82aa2977506 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ShinyUser/tpn002-step750-e82aa2977506

Run and chat with the model

lemonade run user.tpn002-step750-e82aa2977506-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use ShinyUser/tpn002-step750-e82aa2977506 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ShinyUser/tpn002-step750-e82aa2977506

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 ShinyUser/tpn002-step750-e82aa2977506

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ShinyUser/tpn002-step750-e82aa2977506 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ShinyUser/tpn002-step750-e82aa2977506

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 "ShinyUser/tpn002-step750-e82aa2977506" \
  --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"

TPN-002 checkpoint-750 candidate

Private evaluation artifact derived from tpnlabs/tpn-002-base using the checkpoint-750 adapter and the recorded mixed IQ3 quantization plan.

The immutable file identity, training step, size, and local five-task benchmark are recorded in manifest.json.

Downloads last month: 49

GGUF

Model size

9B params

Architecture

qwen35

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