Instructions to use geolazagr/greko with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use geolazagr/greko 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 geolazagr/greko:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf geolazagr/greko:Q4_K_M

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/geolazagr/greko:Q4_K_M

LM Studio
Jan

vLLM

How to use geolazagr/greko with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "geolazagr/greko"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "geolazagr/greko",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/geolazagr/greko:Q4_K_M

Ollama
How to use geolazagr/greko with Ollama:
```
ollama run hf.co/geolazagr/greko:Q4_K_M
```
Unsloth Desktop

How to use geolazagr/greko with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf geolazagr/greko:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "geolazagr/greko:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use geolazagr/greko with Docker Model Runner:
```
docker model run hf.co/geolazagr/greko:Q4_K_M
```

Lemonade

How to use geolazagr/greko with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull geolazagr/greko:Q4_K_M

Run and chat with the model

lemonade run user.greko-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use geolazagr/greko with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf geolazagr/greko: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 geolazagr/greko:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use geolazagr/greko with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf geolazagr/greko: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 "geolazagr/greko: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"

geolazagr commited on 10 days ago

Commit

0edc37f

verified ·

1 Parent(s): 2520a56

Release Greko 2.12-beta (build 25, model 2.3)

Browse files

Files changed (2) hide show

app-version.json +1 -11
greko.apk +2 -2

app-version.json CHANGED Viewed

@@ -1,11 +1 @@
-{
- "versionCode": 23,
- "versionName": "2.10-beta",
- "url": "https://huggingface.co/geolazagr/greko/resolve/main/greko.apk",
- "size": 58926884,
- "sha256": "497b9d82acabf7559d7a5f1131ac9080ee87d9acbcaf6e8dd29082d3c91111e7",
- "notes": {
-  "en": "With web search on, Greko now shows pictures from Wikipedia of what you asked about. Tap one to see it larger.",
-  "el": "Με ανοιχτή την αναζήτηση στον ιστό, ο Greko δείχνει πλέον εικόνες από τη Βικιπαίδεια για αυτό που ρωτήσατε. Πατήστε μία για να τη δείτε μεγαλύτερη."
- }
-}


1	+ {"versionCode": 25, "versionName": "2.12-beta", "url": "https://huggingface.co/geolazagr/greko/resolve/main/greko.apk", "size": 59057144, "sha256": "053c1929c892f2de27fcfed793d48b9c2a59397ef9957f33f724d365dfa86855", "notes": {"en": "Greko 2.3: better Greek, safer answers, emergency numbers when someone may be in danger, and security fixes. Clear the app's storage to get the new model.", "el": "Greko 2.3: καλύτερα ελληνικά, πιο ασφαλείς απαντήσεις, αριθμοί έκτακτης ανάγκης όταν κάποιος μπορεί να κινδυνεύει, και διορθώσεις ασφαλείας. Καθάρισε τα δεδομένα της εφαρμογής για να πάρεις το νέο μοντέλο."}}

greko.apk CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:497b9d82acabf7559d7a5f1131ac9080ee87d9acbcaf6e8dd29082d3c91111e7
-size 58926884

 version https://git-lfs.github.com/spec/v1
+oid sha256:053c1929c892f2de27fcfed793d48b9c2a59397ef9957f33f724d365dfa86855
+size 59057144