Instructions to use mahsery/howdo-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 mahsery/howdo-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 mahsery/howdo-4b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mahsery/howdo-4b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mahsery/howdo-4b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mahsery/howdo-4b:Q4_K_M

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 mahsery/howdo-4b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf mahsery/howdo-4b:Q4_K_M

Use Docker

docker model run hf.co/mahsery/howdo-4b:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use mahsery/howdo-4b with Ollama:
```
ollama run hf.co/mahsery/howdo-4b:Q4_K_M
```
Unsloth Desktop

How to use mahsery/howdo-4b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mahsery/howdo-4b:Q4_K_M

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": "mahsery/howdo-4b:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use mahsery/howdo-4b with Docker Model Runner:
```
docker model run hf.co/mahsery/howdo-4b:Q4_K_M
```

Lemonade

How to use mahsery/howdo-4b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mahsery/howdo-4b:Q4_K_M

Run and chat with the model

lemonade run user.howdo-4b-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use mahsery/howdo-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 mahsery/howdo-4b:Q4_K_M

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 mahsery/howdo-4b:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mahsery/howdo-4b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mahsery/howdo-4b:Q4_K_M

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 "mahsery/howdo-4b:Q4_K_M" \
  --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"

howdo-4b / README.md

mahsery

Upload README.md with huggingface_hub

8bd82f6 verified 2 months ago

preview code

Raw History Blame Contribute Delete

2.44 kB

---
license: apache-2.0
tags:
  - bash
  - shell
  - posix
  - qwen3.5
  - text-to-command
  - gguf
  - llama.cpp
language:
  - en
---
# howdo-4b-v4

`howdo-4b-v4` is a 4.0B parameter language model fine-tuned for single-line natural-language-to-shell-command translation (POSIX and Bash).

The model is designed for fast, local inference with `llama.cpp` and powers the [`howdo`](https://github.com/Mahsery/howdo) CLI tool.

## Model Description

- **Base Architecture**: Qwen3.5-4B (language backbone with vision encoder weights removed to minimize memory footprint and inference latency).
- **Target Task**: Converting natural language terminal requests into precise, single-line POSIX and Bash commands.
- **Quantization**: Q4_K_M GGUF (2.57 GB).
- **Context Length**: 512 tokens (optimized for fast single-turn terminal execution).
- **License**: Apache-2.0.

## Training Details

The model was fine-tuned using LoRA (rank 32, alpha 64) on 69,000 verified command generation examples, with particular focus on:
- Scope boundary enforcement (e.g. non-recursive `-maxdepth 1` constraints).
- Option terminators for leading dashes (e.g. `--` for filenames beginning with `-`).
- Safe pipeline patterns (e.g. `find -print0 | xargs -0`).
- Flag arity and modern CLI replacements (`rg`, `fd`, `jq`, `sed`, `awk`, `tar`).

## Usage

### With howdo CLI

Install the `howdo` tool:

```bash
git clone https://github.com/Mahsery/howdo.git
cd howdo
cargo install --path .
howdo setup
```

Generate commands:

```bash
howdo find all empty directories in the current folder only
```

### With llama.cpp

Run the GGUF model directly using `llama-cli`:

```bash
llama-cli -m howdo-4b-v4-Q4_K_M.gguf \
  -p "<|im_start|>system\nYou are a shell command generator. Output exactly one line: a single POSIX/bash command that accomplishes the user's request. No prose, no markdown fences, no explanation.<|im_end|>\n<|im_start|>user\nfind all empty directories in the current folder only<|im_end|>\n<|im_start|>assistant\n" \
  -n 64 --temp 0.0
```

### Prompt Format

The model expects the ChatML format with a strict single-line instruction system prompt:

```text
<|im_start|>system
You are a shell command generator. Output exactly one line: a single POSIX/bash command that accomplishes the user's request. No prose, no markdown fences, no explanation.<|im_end|>
<|im_start|>user
[Your request in plain English]<|im_end|>
<|im_start|>assistant
```

	---
	license: apache-2.0
	tags:
	- bash
	- shell
	- posix
	- qwen3.5
	- text-to-command
	- gguf
	- llama.cpp
	language:
	- en
	---

	# howdo-4b-v4

	`howdo-4b-v4` is a 4.0B parameter language model fine-tuned for single-line natural-language-to-shell-command translation (POSIX and Bash).

	The model is designed for fast, local inference with `llama.cpp` and powers the [`howdo`](https://github.com/Mahsery/howdo) CLI tool.

	## Model Description

	- Base Architecture: Qwen3.5-4B (language backbone with vision encoder weights removed to minimize memory footprint and inference latency).
	- Target Task: Converting natural language terminal requests into precise, single-line POSIX and Bash commands.
	- Quantization: Q4_K_M GGUF (2.57 GB).
	- Context Length: 512 tokens (optimized for fast single-turn terminal execution).
	- License: Apache-2.0.

	## Training Details

	The model was fine-tuned using LoRA (rank 32, alpha 64) on 69,000 verified command generation examples, with particular focus on:
	- Scope boundary enforcement (e.g. non-recursive `-maxdepth 1` constraints).
	- Option terminators for leading dashes (e.g. `--` for filenames beginning with `-`).
	- Safe pipeline patterns (e.g. `find -print0 \| xargs -0`).
	- Flag arity and modern CLI replacements (`rg`, `fd`, `jq`, `sed`, `awk`, `tar`).

	## Usage

	### With howdo CLI

	Install the `howdo` tool:

	```bash
	git clone https://github.com/Mahsery/howdo.git
	cd howdo
	cargo install --path .
	howdo setup
	```

	Generate commands:

	```bash
	howdo find all empty directories in the current folder only
	```

	### With llama.cpp

	Run the GGUF model directly using `llama-cli`:

	```bash
	llama-cli -m howdo-4b-v4-Q4_K_M.gguf \
	-p "<\|im_start\|>system\nYou are a shell command generator. Output exactly one line: a single POSIX/bash command that accomplishes the user's request. No prose, no markdown fences, no explanation.<\|im_end\|>\n<\|im_start\|>user\nfind all empty directories in the current folder only<\|im_end\|>\n<\|im_start\|>assistant\n" \
	-n 64 --temp 0.0
	```

	### Prompt Format

	The model expects the ChatML format with a strict single-line instruction system prompt:

	```text
	<\|im_start\|>system
	You are a shell command generator. Output exactly one line: a single POSIX/bash command that accomplishes the user's request. No prose, no markdown fences, no explanation.<\|im_end\|>
	<\|im_start\|>user
	[Your request in plain English]<\|im_end\|>
	<\|im_start\|>assistant
	```