Instructions to use TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1")
model = AutoModelForCausalLM.from_pretrained("TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1")
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 TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1",
	filename="Luau-Devstral-24B-Instruct-v0.1-BF16.gguf",
)

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

Inference
Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1: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 TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1: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 TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1:Q4_K_M

Use Docker

docker model run hf.co/TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1:Q4_K_M

LM Studio
Jan

vLLM

How to use TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1:Q4_K_M

SGLang

How to use TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1 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 "TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1" \
    --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": "TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1",
		"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 "TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1" \
        --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": "TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1 with Ollama:
```
ollama run hf.co/TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1:Q4_K_M
```

Unsloth Studio new

How to use TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1 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 TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1 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 TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1 to start chatting

Pi new

How to use TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1: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": "TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1: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 TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1 with Docker Model Runner:
```
docker model run hf.co/TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1:Q4_K_M
```

Lemonade

How to use TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TorpedoSoftware/Luau-Devstral-24B-Instruct-v0.1:Q4_K_M

Run and chat with the model

lemonade run user.Luau-Devstral-24B-Instruct-v0.1-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.

Luau Devstral 24B Instruct v0.1

A Roblox Luau focused finetune of Devstral Small 2507.

Model Details

Model Description

Devstral Small 2507 is a powerful choice for local inference, achieving SOTA open source results at just 24B parameters. However, Roblox gamedev and Luau programming are generally not well represented in LLM training data. This model fine tunes Devstral on a corpus of permissively licensed Luau code and Roblox documentation, improving the model's Luau programming capabilities. Additionally, the jinja chat template contains a default system prompt that steers the model's Luau capabilities even further.

Developed by: Zack Williams (boatbomber)
Funded by: Torpedo Software LLC
License: Apache 2.0
Finetuned from model: unsloth/Devstral-Small-2507

Model Sources

Repository: https://huggingface.co/mistralai/Devstral-Small-2507
Blog: https://mistral.ai/news/devstral-2507

Training Details

Training Data

https://huggingface.co/datasets/TorpedoSoftware/the-luau-stack

25.917M lines of real Luau code, 0.452B tokens. Format:

Repository: {repo_name}
Repository Description: {repo_description}

File Path: `{file_path}`
File Content:
```Lua
{file_content}
```\

https://huggingface.co/datasets/TorpedoSoftware/roblox-info-dump

19.6K pages of multilingual Roblox documentation, 0.149B tokens. Format:
```
Roblox Creator Docs: {url}
```md
{content}
```\
```

Training Process

Trained a LoRA adapter (r=64) at full precision on two epochs of the dataset for a total of 54,630 steps and 43.40 E FLOPs. Then merged the final adapter checkpoint into a BF16 model.

Training Loss Curve

Imatrix Calibration

The imatrix for the GGUF quantizations was computed using 5.73MB of text containing a combination of technical.txt, groups_merged.txt, and content from the-luau-stack & roblox-info-dump. This created an imatrix that is well suited to the specialized tasks this model is designed for while still maintaining broader intelligence as well. While we do provide several quantizations already, the imatrix.gguf is included in this repository should you want to create other quants yourself.