Instructions to use solarpush/push-3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use solarpush/push-3b 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 solarpush/push-3b
# Run inference directly in the terminal:
llama cli -hf solarpush/push-3b

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf solarpush/push-3b
# Run inference directly in the terminal:
llama cli -hf solarpush/push-3b

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf solarpush/push-3b
# Run inference directly in the terminal:
./build/bin/llama cli -hf solarpush/push-3b

Use Docker

docker model run hf.co/solarpush/push-3b

Llama new
LM Studio
Jan
Ollama
How to use solarpush/push-3b with Ollama:
```
ollama run hf.co/solarpush/push-3b
```
Unsloth Desktop

How to use solarpush/push-3b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf solarpush/push-3b

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": "solarpush/push-3b"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use solarpush/push-3b with Docker Model Runner:
```
docker model run hf.co/solarpush/push-3b
```

Lemonade

How to use solarpush/push-3b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull solarpush/push-3b

Run and chat with the model

lemonade run user.push-3b-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use solarpush/push-3b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf solarpush/push-3b

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 solarpush/push-3b

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use solarpush/push-3b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf solarpush/push-3b

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 "solarpush/push-3b" \
  --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"

push-3b

File size: 788 Bytes

435ea01

{
  "temperature": [
    1.843,
    2.1509,
    1.0447
  ],
  "temperature_by_options": {
    "noul:2": 1.0447,
    "score:3-5": 2.1509,
    "choice:2": 1.843,
    "choice:3-5": 1.8658,
    "choice:6-10": 1.7508,
    "choice:11+": 1.5465
  },
  "temperature_range": [
    0.25,
    16.0
  ],
  "baseline_accuracy": {
    "total": 0.6289,
    "choice": 0.5714,
    "score": 0.4099,
    "noul": 0.775
  },
  "oof_accuracy": {
    "total": 0.683,
    "choice": 0.6446,
    "score": 0.516,
    "noul": 0.7876
  },
  "post_quant_accuracy": {
    "total": 0.683,
    "choice": 0.6446,
    "score": 0.516,
    "noul": 0.7876
  },
  "trained_samples": 3050,
  "source": "Trainaya Multi-Stage GGUF Decision Trainer (55/45 Kernel Ridge + Masked Softmax KL+Brier+RPS AdamW, 5-Fold OOF Calibrated)"
}