Instructions to use esc511/trip-optimizer-judge with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use esc511/trip-optimizer-judge with MLX:

# Download the model from the Hub
pip install huggingface_hub[hf_xet]

huggingface-cli download --local-dir trip-optimizer-judge esc511/trip-optimizer-judge

llama-cpp-python

How to use esc511/trip-optimizer-judge with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="esc511/trip-optimizer-judge",
	filename="trip-judge-q4km.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use esc511/trip-optimizer-judge 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 esc511/trip-optimizer-judge
# Run inference directly in the terminal:
llama cli -hf esc511/trip-optimizer-judge

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf esc511/trip-optimizer-judge
# Run inference directly in the terminal:
llama cli -hf esc511/trip-optimizer-judge

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 esc511/trip-optimizer-judge
# Run inference directly in the terminal:
./llama-cli -hf esc511/trip-optimizer-judge

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 esc511/trip-optimizer-judge
# Run inference directly in the terminal:
./build/bin/llama-cli -hf esc511/trip-optimizer-judge

Use Docker

docker model run hf.co/esc511/trip-optimizer-judge

LM Studio
Jan
Ollama
How to use esc511/trip-optimizer-judge with Ollama:
```
ollama run hf.co/esc511/trip-optimizer-judge
```

Unsloth Studio

How to use esc511/trip-optimizer-judge 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 esc511/trip-optimizer-judge 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 esc511/trip-optimizer-judge to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for esc511/trip-optimizer-judge to start chatting

How to use esc511/trip-optimizer-judge with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "esc511/trip-optimizer-judge"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "esc511/trip-optimizer-judge"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use esc511/trip-optimizer-judge with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "esc511/trip-optimizer-judge"

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 esc511/trip-optimizer-judge

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use esc511/trip-optimizer-judge with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "esc511/trip-optimizer-judge"

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 "esc511/trip-optimizer-judge" \
  --custom-provider-id mlx-lm \
  --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 esc511/trip-optimizer-judge with Docker Model Runner:
```
docker model run hf.co/esc511/trip-optimizer-judge
```

Lemonade

How to use esc511/trip-optimizer-judge with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull esc511/trip-optimizer-judge

Run and chat with the model

lemonade run user.trip-optimizer-judge-{{QUANT_TAG}}

List all available models

lemonade list

trip-optimizer-judge / README.md

esc511

Upload folder using huggingface_hub

2a6ad8c verified about 2 months ago

preview code

Raw

History Blame Contribute Delete

1.98 kB

	---
	base_model: Qwen/Qwen3-4B-Instruct-2507
	library_name: mlx
	tags:
	- lora
	- mlx
	- trip-optimizer
	- travel
	- judge
	license: apache-2.0
	---

	# trip-optimizer-judge

	MLX LoRA adapter for Qwen3-4B-Instruct-2507 that assesses violation candidates
	in travel itinerary proposals for [trip-optimizer](https://github.com/michaelpersonal/trip-optimizer).

	## Task

	Given a trip profile, a proposed itinerary change, and deterministically computed
	violation candidates, the model assesses each candidate as `valid`, `invalid`, or
	`uncertain`, with severity (`none/minor/major/critical`) and fixability
	(`none_needed/simple_revision/major_rewrite/terminal`). It also outputs any
	additional violations it detects independently. The final accept/reject/revise
	decision is derived programmatically by trip-optimizer from these assessments.

	Input task field: `assess_violations`

	## Usage with mlx-lm

	```bash
	pip install mlx-lm
	```

	```python
	from mlx_lm import load, generate

	model, tokenizer = load(
	"Qwen/Qwen3-4B-Instruct-2507",
	adapter_path="esc511/trip-optimizer-judge",
	)
	```

	## Usage with trip-optimizer

	```bash
	# After installing trip-optimizer
	trip-optimizer setup # pulls via Ollama
	```

	Or point directly at this adapter by running mlx-lm with it and configuring
	the endpoint in `~/.trip-optimizer/config.json`.

	## Training details

	- Base model: Qwen/Qwen3-4B-Instruct-2507
	- Method: MLX LoRA (r=8, alpha=20, dropout=0)
	- Layers: 32
	- Training iters: 600
	- Max sequence length: 4096
	- Hardware: Apple M5 Max 128 GB
	- Checkpoint: v8 (trip-judge-v1-mlx-r8-v8)

	## Input / Output schema

	Full schemas at:
	- Input: [trip_judge_v1_input.schema.json](https://github.com/michaelpersonal/trip-optimizer/blob/main/finetuning/judge/schemas/trip_judge_v1_input.schema.json)
	- Output: [trip_judge_v1_output.schema.json](https://github.com/michaelpersonal/trip-optimizer/blob/main/finetuning/judge/schemas/trip_judge_v1_output.schema.json)