Instructions to use GitMylo/arpy-tiny-1.7b-v1-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GitMylo/arpy-tiny-1.7b-v1-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="GitMylo/arpy-tiny-1.7b-v1-gguf",
	filename="Arpy-tiny-1.7b-v1-Q8_0.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 GitMylo/arpy-tiny-1.7b-v1-gguf 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 GitMylo/arpy-tiny-1.7b-v1-gguf:Q8_0
# Run inference directly in the terminal:
llama cli -hf GitMylo/arpy-tiny-1.7b-v1-gguf:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf GitMylo/arpy-tiny-1.7b-v1-gguf:Q8_0
# Run inference directly in the terminal:
llama cli -hf GitMylo/arpy-tiny-1.7b-v1-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 GitMylo/arpy-tiny-1.7b-v1-gguf:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf GitMylo/arpy-tiny-1.7b-v1-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 GitMylo/arpy-tiny-1.7b-v1-gguf:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf GitMylo/arpy-tiny-1.7b-v1-gguf:Q8_0

Use Docker

docker model run hf.co/GitMylo/arpy-tiny-1.7b-v1-gguf:Q8_0

LM Studio
Jan
Ollama
How to use GitMylo/arpy-tiny-1.7b-v1-gguf with Ollama:
```
ollama run hf.co/GitMylo/arpy-tiny-1.7b-v1-gguf:Q8_0
```

Unsloth Studio

How to use GitMylo/arpy-tiny-1.7b-v1-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 GitMylo/arpy-tiny-1.7b-v1-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 GitMylo/arpy-tiny-1.7b-v1-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for GitMylo/arpy-tiny-1.7b-v1-gguf to start chatting

How to use GitMylo/arpy-tiny-1.7b-v1-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GitMylo/arpy-tiny-1.7b-v1-gguf:Q8_0

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": "GitMylo/arpy-tiny-1.7b-v1-gguf:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use GitMylo/arpy-tiny-1.7b-v1-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GitMylo/arpy-tiny-1.7b-v1-gguf:Q8_0

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 GitMylo/arpy-tiny-1.7b-v1-gguf:Q8_0

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use GitMylo/arpy-tiny-1.7b-v1-gguf with Docker Model Runner:
```
docker model run hf.co/GitMylo/arpy-tiny-1.7b-v1-gguf:Q8_0
```

Lemonade

How to use GitMylo/arpy-tiny-1.7b-v1-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull GitMylo/arpy-tiny-1.7b-v1-gguf:Q8_0

Run and chat with the model

lemonade run user.arpy-tiny-1.7b-v1-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.

A highly experimental, underfitted tiny language model based on Qwen3 base, then upgraded to use the instruct model's lm head and continued training afterwards.

gguf | safetensors

Goal

To create a model capable of roleplaying as a character, and also think and call tools to allow for interactive npcs in a game for example.
I want a model that's as unbiased (in referring to itself as a certain ai model or similar) as possible.

Training process

Using the following datasets:

First, Qwen3 1.7b base was trained on the datasets to add basic chat and instruct capabilities, for 20 epochs. This created a very incomplete model.
Then, Qwen3 1.7b's (instruct) LM head was added to the model, and the config from instruct was used. Running the model now still gave broken outputs but attempted to use the actual chat tokens.
Finally, this modified model was finetuned for another 20 epochs on the datasets, after which the model became usable, but still underfitted as of now.

Required future fixes

Adding a dataset with more thinking could assist the model with thinking tasks. More training is still needed. Using the smallest dataset size as the step count cap for the datasets would allow for equal use of each dataset instead of the current situation where function calling is used the most.

Recommendations

Use low temperature (like 0.1)
Disable thinking (it doesn't work properly, the model usually responds in thinking)

Known issues

The model is very forgetful
The model doesn't activate tools when it should
The model activates tools when it shouldn't

Downloads last month: 152

GGUF

Model size

2B params

Architecture

qwen3

Hardware compatibility

8-bit

View +1 variant

Inference Providers NEW

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