Instructions to use Depthark/activegotchi-ai with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Depthark/activegotchi-ai with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Depthark/activegotchi-ai",
	filename="activegotchi-ai-v1.0.0-Q4_K_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Depthark/activegotchi-ai 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 Depthark/activegotchi-ai:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Depthark/activegotchi-ai:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Depthark/activegotchi-ai:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Depthark/activegotchi-ai: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 Depthark/activegotchi-ai:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Depthark/activegotchi-ai: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 Depthark/activegotchi-ai:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Depthark/activegotchi-ai:Q4_K_M

Use Docker

docker model run hf.co/Depthark/activegotchi-ai:Q4_K_M

LM Studio
Jan

vLLM

How to use Depthark/activegotchi-ai with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Depthark/activegotchi-ai:Q4_K_M

Ollama
How to use Depthark/activegotchi-ai with Ollama:
```
ollama run hf.co/Depthark/activegotchi-ai:Q4_K_M
```

Unsloth Studio

How to use Depthark/activegotchi-ai 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 Depthark/activegotchi-ai 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 Depthark/activegotchi-ai to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Depthark/activegotchi-ai to start chatting

How to use Depthark/activegotchi-ai with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Depthark/activegotchi-ai: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": "Depthark/activegotchi-ai:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Depthark/activegotchi-ai with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Depthark/activegotchi-ai: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 Depthark/activegotchi-ai:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Depthark/activegotchi-ai with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Depthark/activegotchi-ai:Q4_K_M

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 "Depthark/activegotchi-ai:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --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 Depthark/activegotchi-ai with Docker Model Runner:
```
docker model run hf.co/Depthark/activegotchi-ai:Q4_K_M
```

Lemonade

How to use Depthark/activegotchi-ai with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Depthark/activegotchi-ai:Q4_K_M

Run and chat with the model

lemonade run user.activegotchi-ai-Q4_K_M

List all available models

lemonade list

activegotchi-ai / README.md

Depthark

v1.0.0: model card

6bf588f verified 3 days ago

preview code

Raw

History Blame Contribute Delete

2.91 kB

metadata

license: apache-2.0
base_model: Qwen/Qwen2.5-0.5B-Instruct
base_model_relation: finetune
pipeline_tag: text-generation
library_name: llama.cpp
language:
  - en
  - cs
  - sk
  - de
  - fr
  - es
  - it
  - pt
  - ja
  - ko
  - zh
tags:
  - gguf
  - qwen2.5
  - quantized
  - llama.cpp
  - llama.rn
  - on-device
  - lora
  - companion
  - text-rewriting

ActiveGotchi AI — v1.0.0

A tiny multilingual companion-voice rewriting model. Given a short, pre-computed activity or sleep summary (steps, minutes, hours, streaks), it rewrites the text as a warm, playful letter from a virtual pet — in the requested language, keeping every number, name and emoji exactly as given.

It is a narrow specialist: not a chatbot, not an assistant, not a coach, and not a medical tool.

Lineage


Parent model	Qwen/Qwen2.5-0.5B-Instruct (494M params, Apache-2.0)
Fine-tune	LoRA (2.93M trainable params, ~0.6%), merged into the base
Training	3-stage curriculum (voice → summary rewriting → long-term reviews) + mixed rehearsal pass, on ~1M fully synthetic multilingual samples — no real user data
Quantization	GGUF quants of the merged fine-tune, produced with llama.cpp `llama-quantize`
Released	2026-07-19

Files

File	Size
`activegotchi-ai-v1.0.0-Q4_K_M.gguf`	398 MB
`activegotchi-ai-v1.0.0-Q5_K_M.gguf`	420 MB

Recommended: Q4_K_M — the best size/quality balance for phones and other memory-constrained devices.

Usage

ChatML prompt format, built into the GGUF chat template — llama.cpp, llama.rn, LM Studio, Ollama etc. apply it automatically. Send ONE user message that states the persona/task and ends with the text to rewrite:

You are a small cheerful companion. Rewrite the following daily summary for
your human in your own voice. Keep every number exactly as given, keep it to
3-4 short sentences. Write your entire reply in Czech. Do not use any other
language. SUMMARY TO REWRITE: <template letter with the real numbers>

Suggested inference settings: temperature 0.6, max tokens 220, context 2048.

llama-cli -m activegotchi-ai-v1.0.0-Q4_K_M.gguf -st \
  -p "<prompt as above>" -n 220 --temp 0.6

Trained behavior

Never emits a number that is not present in the prompt.
Replies only in the language the prompt pins.
Short letters (3–6 sentences), no greetings, no filler.
Warm, non-judgmental tone; no medical advice, diagnosis or shaming.

Limitations

The model only knows what the prompt contains — it has no memory, no health knowledge, and no general-assistant abilities. Outside its rewrite task, output quality is undefined. Languages beyond en/cs/de/es/fr received less training weight. Synthetic-data style ceiling applies.

Release notes

Automated release from run_full_flow_mac.sh