Instructions to use ShinyUser/tpn001-T12-0b3ee1d305d5 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/tpn001-T12-0b3ee1d305d5 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/tpn001-T12-0b3ee1d305d5
# Run inference directly in the terminal:
llama cli -hf ShinyUser/tpn001-T12-0b3ee1d305d5

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ShinyUser/tpn001-T12-0b3ee1d305d5
# Run inference directly in the terminal:
llama cli -hf ShinyUser/tpn001-T12-0b3ee1d305d5

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/tpn001-T12-0b3ee1d305d5
# Run inference directly in the terminal:
./llama-cli -hf ShinyUser/tpn001-T12-0b3ee1d305d5

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/tpn001-T12-0b3ee1d305d5
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ShinyUser/tpn001-T12-0b3ee1d305d5

Use Docker

docker model run hf.co/ShinyUser/tpn001-T12-0b3ee1d305d5

LM Studio
Jan
Ollama
How to use ShinyUser/tpn001-T12-0b3ee1d305d5 with Ollama:
```
ollama run hf.co/ShinyUser/tpn001-T12-0b3ee1d305d5
```

Unsloth Studio

How to use ShinyUser/tpn001-T12-0b3ee1d305d5 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 ShinyUser/tpn001-T12-0b3ee1d305d5 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 ShinyUser/tpn001-T12-0b3ee1d305d5 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ShinyUser/tpn001-T12-0b3ee1d305d5 to start chatting

How to use ShinyUser/tpn001-T12-0b3ee1d305d5 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ShinyUser/tpn001-T12-0b3ee1d305d5

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/tpn001-T12-0b3ee1d305d5"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ShinyUser/tpn001-T12-0b3ee1d305d5 with Docker Model Runner:
```
docker model run hf.co/ShinyUser/tpn001-T12-0b3ee1d305d5
```

Lemonade

How to use ShinyUser/tpn001-T12-0b3ee1d305d5 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ShinyUser/tpn001-T12-0b3ee1d305d5

Run and chat with the model

lemonade run user.tpn001-T12-0b3ee1d305d5-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use ShinyUser/tpn001-T12-0b3ee1d305d5 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/tpn001-T12-0b3ee1d305d5

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/tpn001-T12-0b3ee1d305d5

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ShinyUser/tpn001-T12-0b3ee1d305d5 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ShinyUser/tpn001-T12-0b3ee1d305d5

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/tpn001-T12-0b3ee1d305d5" \
  --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.

TPN-001 T12 benchmarked candidate

This private repository preserves the exact T12 GGUF evaluated locally with the corrected llama.cpp b10020 evaluator.

GGUF SHA256: 0b3ee1d305d5fffffbd11fa17e3dfb88d882f8198e62857a3c1dd9356ec46516
MMLU (acc,none): 0.639083
HellaSwag (acc_norm,none): 0.9187412865962955
Weighted composite: 0.7229804859788886
Provenance CKA: 1.0000
RAM margin: 35546727 bytes

This model passes the live TPN-001 competition's published minimum-score requirements (0.0 for both tasks) and its RAM ceiling. The 0.6800 MMLU and 0.7310 composite thresholds used during development were internal stretch targets, not live competition eligibility requirements. Scores above are local evaluator-aligned measurements, not protected TPN Bench results.

The revision intentionally contains exactly one GGUF, one JSON manifest, and this README.

Downloads last month: 29

GGUF

Model size

2B 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