Instructions to use build-small-hackathon/limp-mode-leap1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use build-small-hackathon/limp-mode-leap1 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="build-small-hackathon/limp-mode-leap1",
	filename="limpmode-leap1-Q4_K_M.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 build-small-hackathon/limp-mode-leap1 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf build-small-hackathon/limp-mode-leap1:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf build-small-hackathon/limp-mode-leap1:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf build-small-hackathon/limp-mode-leap1:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf build-small-hackathon/limp-mode-leap1: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 build-small-hackathon/limp-mode-leap1:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf build-small-hackathon/limp-mode-leap1: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 build-small-hackathon/limp-mode-leap1:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf build-small-hackathon/limp-mode-leap1:Q4_K_M

Use Docker

docker model run hf.co/build-small-hackathon/limp-mode-leap1:Q4_K_M

LM Studio
Jan

vLLM

How to use build-small-hackathon/limp-mode-leap1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "build-small-hackathon/limp-mode-leap1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "build-small-hackathon/limp-mode-leap1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/build-small-hackathon/limp-mode-leap1:Q4_K_M

Ollama
How to use build-small-hackathon/limp-mode-leap1 with Ollama:
```
ollama run hf.co/build-small-hackathon/limp-mode-leap1:Q4_K_M
```

Unsloth Studio

How to use build-small-hackathon/limp-mode-leap1 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 build-small-hackathon/limp-mode-leap1 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 build-small-hackathon/limp-mode-leap1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for build-small-hackathon/limp-mode-leap1 to start chatting

How to use build-small-hackathon/limp-mode-leap1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf build-small-hackathon/limp-mode-leap1: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": "build-small-hackathon/limp-mode-leap1:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use build-small-hackathon/limp-mode-leap1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf build-small-hackathon/limp-mode-leap1: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 build-small-hackathon/limp-mode-leap1:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use build-small-hackathon/limp-mode-leap1 with Docker Model Runner:
```
docker model run hf.co/build-small-hackathon/limp-mode-leap1:Q4_K_M
```

Lemonade

How to use build-small-hackathon/limp-mode-leap1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull build-small-hackathon/limp-mode-leap1:Q4_K_M

Run and chat with the model

lemonade run user.limp-mode-leap1-Q4_K_M

List all available models

lemonade list

limp-mode-leap1: roadside triage fine-tune of Qwen3.5-4B

The brain of Limp Mode, an offline roadside copilot. Fine-tuned to read a driver's messy description of a car problem and answer a strict-JSON triage verdict: STOP / CAUTION / DRIVE, plain-language reasoning, over-inclusive hazard flags (they feed a deterministic safety floor downstream), no-tools roadside checks, a self-rescue plan adapted to how far help is, and an anti-upsell script for the mechanic. English and Spanish.

Training

Data: [N] examples, synthetic conversations from a frontier teacher grounded in verified knowledge bases (3,369 OBD codes, 64 ISO dashboard symbols, 38 hidden-gotcha entries, 15 roadside procedures), passed through deterministic quality gates: JSON schema, severity-floor consistency, enum vocabulary, knowledge grounding, 4-gram dedup, and n-gram decontamination against the eval suite. Includes adversarial slices: noisy retrievals whose correct answer ignores the provided context, and benign cases that punish overcaution.
Method: LoRA (r=32, alpha=64, completion-only loss) via Unsloth on Modal (L40S), thinking disabled, 3 epochs.
Formats: LoRA adapter, merged fp16, and GGUF Q4_K_M for llama.cpp.

Evaluation: 202-case golden suite

Safety-asymmetric metrics; "dangerous-as-safe" (expected STOP, answered DRIVE) must be 0. Both rows are measured through the identical pipeline, so the difference is the fine-tune.

stage	verdict accuracy	dangerous-as-safe	schema valid	knowledge surfaced
base Qwen3.5-4B, full pipeline	83.2%	0	99.5%	98.9%
this model, full pipeline	92.6%	0	100%	97.9%

Per category, the fine-tuned model scores 100% on OBD-code and dashboard-symbol cases, 94.6% on hidden-cause cases, and 91.5% on free-form judgment. The honest soft spots are benign cases (81%, a little residual overcaution) and Spanish (84%).

Eval harness, suite, and full traces are public: https://huggingface.co/datasets/build-small-hackathon/limp-mode-traces

Usage

Deployed inside Limp Mode's pipeline: deterministic intake (symbols/OBD) → IDF retrieval over the gotchas KB → this model (strict JSON contract) → deterministic severity floor that can raise but never lower the verdict. Use the system prompt from the Space repo's app/pipeline.py for faithful behavior.

llama-server -m limpmode-leap1-Q4_K_M.gguf --port 8080 -ngl 99

Limitations

A 4B model for safety-adjacent advice: it is deliberately caged. The surrounding app never lets it downgrade hard-evidence emergencies, never lets it paraphrase verified procedures, and shows the user every safety override. Use it with the cage.

Downloads last month: 8

GGUF

Model size

4B params

Architecture

qwen35

Hardware compatibility

4-bit

Model tree for build-small-hackathon/limp-mode-leap1

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Quantized

(241)

this model