Instructions to use sahellx/kitty-bash-llm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sahellx/kitty-bash-llm with Transformers:

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

pipe = pipeline("text-generation", model="sahellx/kitty-bash-llm")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sahellx/kitty-bash-llm")
model = AutoModelForCausalLM.from_pretrained("sahellx/kitty-bash-llm", device_map="auto")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use sahellx/kitty-bash-llm 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 sahellx/kitty-bash-llm:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf sahellx/kitty-bash-llm:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf sahellx/kitty-bash-llm:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf sahellx/kitty-bash-llm: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 sahellx/kitty-bash-llm:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf sahellx/kitty-bash-llm: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 sahellx/kitty-bash-llm:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf sahellx/kitty-bash-llm:Q4_K_M

Use Docker

docker model run hf.co/sahellx/kitty-bash-llm:Q4_K_M

LM Studio
Jan

vLLM

How to use sahellx/kitty-bash-llm with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/sahellx/kitty-bash-llm:Q4_K_M

SGLang

How to use sahellx/kitty-bash-llm 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 "sahellx/kitty-bash-llm" \
    --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": "sahellx/kitty-bash-llm",
		"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 "sahellx/kitty-bash-llm" \
        --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": "sahellx/kitty-bash-llm",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use sahellx/kitty-bash-llm with Ollama:
```
ollama run hf.co/sahellx/kitty-bash-llm:Q4_K_M
```
Unsloth Desktop

How to use sahellx/kitty-bash-llm with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf sahellx/kitty-bash-llm: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": "sahellx/kitty-bash-llm:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use sahellx/kitty-bash-llm with Docker Model Runner:
```
docker model run hf.co/sahellx/kitty-bash-llm:Q4_K_M
```

Lemonade

How to use sahellx/kitty-bash-llm with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull sahellx/kitty-bash-llm:Q4_K_M

Run and chat with the model

lemonade run user.kitty-bash-llm-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use sahellx/kitty-bash-llm with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf sahellx/kitty-bash-llm: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 sahellx/kitty-bash-llm:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use sahellx/kitty-bash-llm with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf sahellx/kitty-bash-llm: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 "sahellx/kitty-bash-llm: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"

sahellx commited on 6 days ago

Commit

d05611f

verified ·

1 Parent(s): 857f24b

Add peer comparison with methodology caveats

Browse files

Files changed (1) hide show

README.md +42 -0

README.md CHANGED Viewed

@@ -151,6 +151,48 @@ variable is the fine-tuning. 100 examples per task.
 > `--rm ubuntu` is not valid standalone bash); the meaningful figure is
 > prefix + completion, at **99.29%**.
 ShellCheck is used because `bash -n` only proves a command *parses*. ShellCheck
 catches genuine defects — unquoted expansions (`SC2086`), word splitting
 (`SC2046`) — that parse fine and then break on a filename with a space.

 > `--rm ubuntu` is not valid standalone bash); the meaningful figure is
 > prefix + completion, at **99.29%**.
+### Comparison with other shell-focused models
+Alongside the base-model comparison above, an **informal** benchmark was run against
+four other publicly available fine-tunes for shell/linux command generation, all at
+Q4_K_M (except where a repo ships only f16), through llama.cpp on the same 2-thread
+CPU, using the same 80 held-out prompts.
+| model | params | size | utility acc | token F1 | s/cmd |
+|---|---|---|---|---|---|
+| **Kitty Bash LLM** | **0.5B** | **398 MB** | **78.75** | **59.54** | **1.68** |
+| `louisguthmann/qwen3.5-2b-shellcommand-linux` | 2.0B | 1274 MB | 63.75 | 32.02 | 15.39 |
+| `vitali87/shell-commands-qwen2-1.5b-extended` | 1.5B | 3094 MB | 57.50 | 33.93 | 9.48 |
+| `mecha-org/linux-command-generator-llama3.2-1b` | 1.0B | 808 MB | 52.50 | 34.21 | 2.78 |
+| `chamibuddhika/linux-commands-0407-00` | — | 1709 MB | — | — | — |
+> #### ⚠️ Please read this before citing the table
+>
+> **This is indicative, not a controlled evaluation.** Four specific caveats, all of
+> which favour this model:
+>
+> 1. **The test set is drawn from this model's own training distribution.** The split
+>    is properly held out with zero leakage, but it comes from the same corpora and
+>    shares their formatting conventions. The other models never saw that style. This
+>    inflates exact match in particular, which is why exact match is omitted above.
+> 2. **All models received *this* model's system prompt.** Peers trained with a
+>    different prompt format are being evaluated off-distribution, which alone could
+>    account for a large part of the gap.
+> 3. **n = 80.** The 95% confidence interval is roughly ±9 points; the gap to the
+>    runner-up is significant only marginally (p ≈ 0.03).
+> 4. **`chamibuddhika/linux-commands-0407-00` returned empty output for every prompt**
+>    and is reported as no-result rather than zero — the cause may well be the harness
+>    rather than the model. `qwen3.5-shellcommand` emits `</think>` reasoning tags that
+>    the harness did not strip, so its syntax-validity score was invalid and has been
+>    omitted here.
+>
+> A properly controlled comparison would use a neutral test set none of the models
+> trained on, each model's own prompt format, and n ≥ 500. Treat the ordering above as
+> a hint worth verifying, not a settled result.
+>
+> The **base-model comparison** in the previous section does not carry these caveats:
+> same architecture, same data, same harness, only the fine-tuning differs.
 ShellCheck is used because `bash -n` only proves a command *parses*. ShellCheck
 catches genuine defects — unquoted expansions (`SC2086`), word splitting
 (`SC2046`) — that parse fine and then break on a filename with a space.