Instructions to use fableforge-ai/ShellWhisperer-1.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fableforge-ai/ShellWhisperer-1.5B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="fableforge-ai/ShellWhisperer-1.5B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fableforge-ai/ShellWhisperer-1.5B")
model = AutoModelForCausalLM.from_pretrained("fableforge-ai/ShellWhisperer-1.5B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use fableforge-ai/ShellWhisperer-1.5B with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="fableforge-ai/ShellWhisperer-1.5B",
	filename="shellwhisperer-1.5b-Q2_K.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use fableforge-ai/ShellWhisperer-1.5B 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 fableforge-ai/ShellWhisperer-1.5B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf fableforge-ai/ShellWhisperer-1.5B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf fableforge-ai/ShellWhisperer-1.5B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf fableforge-ai/ShellWhisperer-1.5B:Q4_K_M

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 fableforge-ai/ShellWhisperer-1.5B:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf fableforge-ai/ShellWhisperer-1.5B:Q4_K_M

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 fableforge-ai/ShellWhisperer-1.5B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf fableforge-ai/ShellWhisperer-1.5B:Q4_K_M

Use Docker

docker model run hf.co/fableforge-ai/ShellWhisperer-1.5B:Q4_K_M

LM Studio
Jan

vLLM

How to use fableforge-ai/ShellWhisperer-1.5B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fableforge-ai/ShellWhisperer-1.5B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fableforge-ai/ShellWhisperer-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fableforge-ai/ShellWhisperer-1.5B:Q4_K_M

SGLang

How to use fableforge-ai/ShellWhisperer-1.5B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "fableforge-ai/ShellWhisperer-1.5B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fableforge-ai/ShellWhisperer-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "fableforge-ai/ShellWhisperer-1.5B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fableforge-ai/ShellWhisperer-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use fableforge-ai/ShellWhisperer-1.5B with Ollama:
```
ollama run hf.co/fableforge-ai/ShellWhisperer-1.5B:Q4_K_M
```

Unsloth Studio

How to use fableforge-ai/ShellWhisperer-1.5B 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 fableforge-ai/ShellWhisperer-1.5B 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 fableforge-ai/ShellWhisperer-1.5B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for fableforge-ai/ShellWhisperer-1.5B to start chatting

How to use fableforge-ai/ShellWhisperer-1.5B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf fableforge-ai/ShellWhisperer-1.5B:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "fableforge-ai/ShellWhisperer-1.5B:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use fableforge-ai/ShellWhisperer-1.5B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf fableforge-ai/ShellWhisperer-1.5B: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 fableforge-ai/ShellWhisperer-1.5B:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use fableforge-ai/ShellWhisperer-1.5B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf fableforge-ai/ShellWhisperer-1.5B: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 "fableforge-ai/ShellWhisperer-1.5B: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"

Docker Model Runner
How to use fableforge-ai/ShellWhisperer-1.5B with Docker Model Runner:
```
docker model run hf.co/fableforge-ai/ShellWhisperer-1.5B:Q4_K_M
```

Lemonade

How to use fableforge-ai/ShellWhisperer-1.5B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull fableforge-ai/ShellWhisperer-1.5B:Q4_K_M

Run and chat with the model

lemonade run user.ShellWhisperer-1.5B-Q4_K_M

List all available models

lemonade list

Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

ShellWhisperer-1.5B — Ultra-Fast Shell Command Assistant

1,100+ downloads · 986MB · 20+ tok/s · Runs on anything

What Is This?

ShellWhisperer is the fastest shell command assistant on the planet. At just 986MB (Q4_K_M), it runs on everything from a Raspberry Pi to a gaming PC. Fine-tuned from Qwen2.5-0.5B on 100K+ shell command traces, it predicts bash, zsh, PowerShell, and DevOps commands with uncanny accuracy.

Unlike general models that kind of know shell commands, ShellWhisperer was trained exclusively on shell tasks — it doesn't write poetry, it gets you the right command fast.

Quick Start

Ollama (recommended)

ollama run FableForge-AI/shellwhisperer

llama.cpp

./llama-cli -m shellwhisperer-1.5b-Q4_K_M.gguf --prompt "find all files larger than 100MB" -n 512

Python

from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("fableforge-ai/ShellWhisperer-1.5B")

Quantizations

File	Size	Speed	Best For
`Q2_K.gguf`	645 MB	~25 tok/s	Phone, Raspberry Pi
`Q3_K_M.gguf`	786 MB	~22 tok/s	Low-end devices
`Q4_0.gguf`	895 MB	~28 tok/s	Fast inference
`Q4_K_M.gguf`	940 MB	~22 tok/s	Recommended
`Q5_K_M.gguf`	1.0 GB	~18 tok/s	High quality
`Q6_K.gguf`	1.2 GB	~15 tok/s	Pro quality
`Q8_0.gguf`	1.5 GB	~12 tok/s	Near-lossless
`f16.gguf`	2.9 GB	~8 tok/s	Full precision

Hardware Requirements

Hardware	Can Run?	Best Quant
Phone (2GB+ RAM)	CPU	Q2_K
Raspberry Pi Zero	CPU	Q2_K
Old laptop (4GB RAM)	CPU	Q4_K_M
Gaming PC (RTX 3060+)	Full GPU	Q5_K_M
Mac M1/M2	Full GPU	Q4_K_M
Server (32GB+)	Full GPU	Q8_0 / F16

Why ShellWhisperer?

Feature	ShellWhisperer	GPT-4	Llama 3.1 8B
Size	986 MB	N/A	4.8 GB
Speed	~22 tok/s CPU	API only	~8 tok/s CPU
Shell accuracy	100K+ shell examples	General	General
Runs on phone	✅ Yes	❌ No	❌ No
Offline	✅ Yes	❌ No	⚠️ Partial

Examples in Action

User: find all files modified in last 7 days
ShellWhisperer: find / -type f -mtime -7 2>/dev/null | head -20

User: check disk usage of all mounted drives sorted by usage
ShellWhisperer: df -h | grep -v tmpfs | sort -k5 -hr

User: list all running Docker containers with ports
ShellWhisperer: docker ps --format "table {{.Names}}\t{{.Ports}}\t{{.Status}}"

User: undo last commit but keep changes in working directory
ShellWhisperer: git reset --soft HEAD~1

User: find which process is listening on port 8080
ShellWhisperer: lsof -i :8080 | grep LISTEN

Training Details

Parameter	Value
Base Model	Qwen2.5-0.5B
Training Data	100K+ shell command traces from Fable5
Context Window	32K tokens
Quantization	imatrix-guided via llama.cpp
License	Apache 2.0

FableForge Ecosystem

Model	Size	Best For
ShellWhisperer ⭐	986 MB	Shell commands, ultra-fast
ReasonCritic-7B	3.1-16 GB	Reasoning + uncensored
NEXUS-Coder	488 MB - 2.9 GB	Domain coding
NEXUS-Security	488 MB - 2.9 GB	Cybersecurity
NEXUS-Medical	488 MB - 2.9 GB	Medical
NEXUS-Legal	488 MB - 2.9 GB	Legal
NEXUS-Finance	488 MB - 2.9 GB	Finance
NEXUS-Science	488 MB - 2.9 GB	Science

License

Apache 2.0 — commercial use allowed.

Part of the FableForge AI ecosystem. Zero Limits. Pure Intelligence.

Downloads last month: 2,007

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for fableforge-ai/ShellWhisperer-1.5B

Base model

Qwen/Qwen2.5-0.5B

Finetuned

(640)

this model

Finetunes

1 model

Quantizations

7 models