Instructions to use TorpedoSoftware/R1-Distill-Qwen-1.5B-Roblox-Luau with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use TorpedoSoftware/R1-Distill-Qwen-1.5B-Roblox-Luau 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 TorpedoSoftware/R1-Distill-Qwen-1.5B-Roblox-Luau:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TorpedoSoftware/R1-Distill-Qwen-1.5B-Roblox-Luau:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf TorpedoSoftware/R1-Distill-Qwen-1.5B-Roblox-Luau:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TorpedoSoftware/R1-Distill-Qwen-1.5B-Roblox-Luau: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/R1-Distill-Qwen-1.5B-Roblox-Luau:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf TorpedoSoftware/R1-Distill-Qwen-1.5B-Roblox-Luau: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/R1-Distill-Qwen-1.5B-Roblox-Luau:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TorpedoSoftware/R1-Distill-Qwen-1.5B-Roblox-Luau:Q4_K_M

Use Docker

docker model run hf.co/TorpedoSoftware/R1-Distill-Qwen-1.5B-Roblox-Luau:Q4_K_M

LM Studio
Jan

vLLM

How to use TorpedoSoftware/R1-Distill-Qwen-1.5B-Roblox-Luau with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TorpedoSoftware/R1-Distill-Qwen-1.5B-Roblox-Luau"
# 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/R1-Distill-Qwen-1.5B-Roblox-Luau",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TorpedoSoftware/R1-Distill-Qwen-1.5B-Roblox-Luau:Q4_K_M

Ollama
How to use TorpedoSoftware/R1-Distill-Qwen-1.5B-Roblox-Luau with Ollama:
```
ollama run hf.co/TorpedoSoftware/R1-Distill-Qwen-1.5B-Roblox-Luau:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use TorpedoSoftware/R1-Distill-Qwen-1.5B-Roblox-Luau with Docker Model Runner:
```
docker model run hf.co/TorpedoSoftware/R1-Distill-Qwen-1.5B-Roblox-Luau:Q4_K_M
```

Lemonade

How to use TorpedoSoftware/R1-Distill-Qwen-1.5B-Roblox-Luau with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TorpedoSoftware/R1-Distill-Qwen-1.5B-Roblox-Luau:Q4_K_M

Run and chat with the model

lemonade run user.R1-Distill-Qwen-1.5B-Roblox-Luau-Q4_K_M

List all available models

lemonade list

Atomic Chat

R1-Distill-Qwen-1.5B-Roblox-Luau

A fine tune of deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B using boatbomber/roblox-info-dump and boatbomber/the-luau-stack for Roblox domain knowledge.

This is intended to be used for speculative decoding with boatbomber/R1-Distill-Qwen-14B-Roblox-Luau. It can be used standalone in memory constrained environments, but is not nearly as capable as the 14B model as it has so few weights that it cannot learn the same level of detail.

Recommended inference settings:

Parameter	Value	Notes
System Prompt	`You are an expert Roblox developer and Luau software engineer.`	Model was fine tuned with this prompt.
temperature	`0.5-0.7`	Underlying R1 Distill uses this. I've found best results with `0.55`.
top_p	`0.95`	Underlying R1 Distill uses this.

Quantization done using Unsloth.

Available quants:

Quant	Size	Notes
F16	3.56GB	Retains 100% accuracy. Slow and memory hungry.
Q8_O	1.89GB	High resource use, but generally acceptable. Use when accuracy is crucial.
Q6_K	1.46GB	Uses Q6_K for all tensors. Good for high end GPUs.
Q5_K_M	1.29GB	Recommended. Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q5_K
Q4_K_M	1.12GB	Recommended. Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q4_K
Q3_K_M	0.92GB	Uses Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else Q3_K. Quality is noticeably degraded.

Downloads last month: 179

Safetensors

Model size

2B params

Tensor type

F32

Model tree for TorpedoSoftware/R1-Distill-Qwen-1.5B-Roblox-Luau

Base model

deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B

Finetuned

(653)

this model

TorpedoSoftware
/

R1-Distill-Qwen-1.5B-Roblox-Luau

R1-Distill-Qwen-1.5B-Roblox-Luau

Model tree for TorpedoSoftware/R1-Distill-Qwen-1.5B-Roblox-Luau

Dataset used to train TorpedoSoftware/R1-Distill-Qwen-1.5B-Roblox-Luau