Instructions to use ThoughtfulThings/phi-2-light-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ThoughtfulThings/phi-2-light-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ThoughtfulThings/phi-2-light-gguf",
	filename="phi-2-light-Q8_0.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use ThoughtfulThings/phi-2-light-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ThoughtfulThings/phi-2-light-gguf:Q8_0
# Run inference directly in the terminal:
llama-cli -hf ThoughtfulThings/phi-2-light-gguf:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ThoughtfulThings/phi-2-light-gguf:Q8_0
# Run inference directly in the terminal:
llama-cli -hf ThoughtfulThings/phi-2-light-gguf:Q8_0

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 ThoughtfulThings/phi-2-light-gguf:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf ThoughtfulThings/phi-2-light-gguf:Q8_0

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 ThoughtfulThings/phi-2-light-gguf:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ThoughtfulThings/phi-2-light-gguf:Q8_0

Use Docker

docker model run hf.co/ThoughtfulThings/phi-2-light-gguf:Q8_0

LM Studio
Jan
Ollama
How to use ThoughtfulThings/phi-2-light-gguf with Ollama:
```
ollama run hf.co/ThoughtfulThings/phi-2-light-gguf:Q8_0
```

Unsloth Studio new

How to use ThoughtfulThings/phi-2-light-gguf 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 ThoughtfulThings/phi-2-light-gguf 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 ThoughtfulThings/phi-2-light-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ThoughtfulThings/phi-2-light-gguf to start chatting

Docker Model Runner
How to use ThoughtfulThings/phi-2-light-gguf with Docker Model Runner:
```
docker model run hf.co/ThoughtfulThings/phi-2-light-gguf:Q8_0
```

Lemonade

How to use ThoughtfulThings/phi-2-light-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ThoughtfulThings/phi-2-light-gguf:Q8_0

Run and chat with the model

lemonade run user.phi-2-light-gguf-Q8_0

List all available models

lemonade list

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Thoughtful Lamp

These are the weights in gguf format for the "thoughtful lamp" from our paper Teaching Things To Think: Bootstrapping Local Reasoning for Smart(er) Devices.

The base model has been fine-tuned to take "action" and "explanation" oriented commands that a user might give to a smart lamp and generate either JSON actions or natural language explanations in response.

Please refer to the GitHub repo for more information.

Prompt Structure

The models are fine-tuned to accept prompts in this format:

Action

User: {command}
[SENSORS] {sensor json} [/SENSORS]
Output: [SETTINGS]

Introspection

User: {command}
[SENSORS] {sensor json} [/SENSORS]
[SETTINGS] {settings json} [/SETTINGS]
Output: [EXPLANATION]

Citation

If our work is helpful, please cite us:

@inproceedings{king2025teaching,
  title={Teaching Things To Think: Bootstrapping Local Reasoning for Smart (er) Devices},
  author={King, Evan and Yu, Haoxiang and Vartak, Sahil and Jacob, Jenna and Lee, Sangsu and Julien, Christine},
  booktitle={2025 IEEE International Conference on Pervasive Computing and Communications (PerCom)},
  pages={78--88},
  year={2025},
  organization={IEEE}
}

Contact

Contact Evan King with questions, or open an issue on the repository.

Downloads last month: 9

GGUF

Model size

3B params

Architecture

phi2

Hardware compatibility

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support