Instructions to use tanepiper/termite-command-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use tanepiper/termite-command-4b 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 tanepiper/termite-command-4b:Q8_0
# Run inference directly in the terminal:
llama cli -hf tanepiper/termite-command-4b:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tanepiper/termite-command-4b:Q8_0
# Run inference directly in the terminal:
llama cli -hf tanepiper/termite-command-4b:Q8_0

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 tanepiper/termite-command-4b:Q8_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf tanepiper/termite-command-4b:Q8_0

Use Docker

docker model run hf.co/tanepiper/termite-command-4b:Q8_0

Llama new
LM Studio
Jan

vLLM

How to use tanepiper/termite-command-4b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tanepiper/termite-command-4b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tanepiper/termite-command-4b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tanepiper/termite-command-4b:Q8_0

Ollama
How to use tanepiper/termite-command-4b with Ollama:
```
ollama run hf.co/tanepiper/termite-command-4b:Q8_0
```
Unsloth Desktop

How to use tanepiper/termite-command-4b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tanepiper/termite-command-4b:Q8_0

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": "tanepiper/termite-command-4b:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use tanepiper/termite-command-4b with Docker Model Runner:
```
docker model run hf.co/tanepiper/termite-command-4b:Q8_0
```

Lemonade

How to use tanepiper/termite-command-4b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tanepiper/termite-command-4b:Q8_0

Run and chat with the model

lemonade run user.termite-command-4b-Q8_0

List all available models

lemonade list

Hermes Agent

How to use tanepiper/termite-command-4b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tanepiper/termite-command-4b:Q8_0

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 tanepiper/termite-command-4b:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use tanepiper/termite-command-4b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tanepiper/termite-command-4b:Q8_0

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 "tanepiper/termite-command-4b:Q8_0" \
  --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"

tanepiper commited on 3 days ago

Commit

a685664

verified ·

1 Parent(s): c45f1ed

Update ports, Linux note and release link

Browse files

Files changed (1) hide show

README.md +4 -2

README.md CHANGED Viewed

@@ -21,7 +21,7 @@ This model turns a request into shell commands, and refuses hostile requests. It
 ## Use it
 ```bash
-llama-server -hf tanepiper/termite-command-4b:Q8_0 --jinja -c 8192 --port 11434
 ```
 Then run `tmite setup`, or set `model_url` and `model` in termite's config. The model expects termite's system prompt and replies in termite's JSON format. With any other prompt, the scores below don't apply.
@@ -59,6 +59,8 @@ Everyday commands ran in a throwaway Linux machine with no network card. These a
 None of the commands from 0.1 was broken by a bad option. The previous run had 3. The base model still does better on our test, because it often gives several commands.
 ## Known limits
 - **It usually gives one command.** It gave two or more on 12.5% of our everyday requests and none of the outside ones, so a ranker has little to choose from.
@@ -68,7 +70,7 @@ None of the commands from 0.1 was broken by a bad option. The previous run had 3
 - **It can answer a greeting with a command.** A request with no job in it, such as "hello", may get an unrelated command.
 - **It sometimes answers what it should refuse.** It wrote a command for 2 of the 30 outside prompt injection requests. Neither was rated a hazard.
 - **The main test has been read closely.** It was used to choose between runs, so 3 of 100 and 40 of 40 are likely to flatter the model. The outside results are stronger evidence, but they are small samples.
-- **Only part of it was tested on Linux.** The full tests ran on macOS. On Linux, the file was loaded and checked with a few requests.
 - **English only.** A few refusal rows are in German and French. Nothing else was tested.
 ## Training

 ## Use it
 ```bash
+llama-server -hf tanepiper/termite-command-4b:Q8_0 --jinja -c 8192 --port 8080
 ```
 Then run `tmite setup`, or set `model_url` and `model` in termite's config. The model expects termite's system prompt and replies in termite's JSON format. With any other prompt, the scores below don't apply.
 None of the commands from 0.1 was broken by a bad option. The previous run had 3. The base model still does better on our test, because it often gives several commands.
+[What changed in each release](https://tanepiper.github.io/termite/models/termite/) compares each version with the one before it.
 ## Known limits
 - **It usually gives one command.** It gave two or more on 12.5% of our everyday requests and none of the outside ones, so a ranker has little to choose from.
 - **It can answer a greeting with a command.** A request with no job in it, such as "hello", may get an unrelated command.
 - **It sometimes answers what it should refuse.** It wrote a command for 2 of the 30 outside prompt injection requests. Neither was rated a hazard.
 - **The main test has been read closely.** It was used to choose between runs, so 3 of 100 and 40 of 40 are likely to flatter the model. The outside results are stronger evidence, but they are small samples.
+- **Only part of it was tested on Linux.** The full tests ran on macOS. On Linux, the file was loaded and checked with a few requests on a GPU. Two hosted CPU jobs loaded it but gave no answer in time, and the cause was not found.
 - **English only.** A few refusal rows are in German and French. Nothing else was tested.
 ## Training