Instructions to use oytunistrator/olang-language-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use oytunistrator/olang-language-model with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="oytunistrator/olang-language-model")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("oytunistrator/olang-language-model", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use oytunistrator/olang-language-model 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 oytunistrator/olang-language-model:F16
# Run inference directly in the terminal:
llama cli -hf oytunistrator/olang-language-model:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf oytunistrator/olang-language-model:F16
# Run inference directly in the terminal:
llama cli -hf oytunistrator/olang-language-model:F16

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf oytunistrator/olang-language-model:F16
# Run inference directly in the terminal:
./build/bin/llama cli -hf oytunistrator/olang-language-model:F16

Use Docker

docker model run hf.co/oytunistrator/olang-language-model:F16

Llama new
LM Studio
Jan

vLLM

How to use oytunistrator/olang-language-model with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/oytunistrator/olang-language-model:F16

SGLang

How to use oytunistrator/olang-language-model with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "oytunistrator/olang-language-model" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "oytunistrator/olang-language-model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "oytunistrator/olang-language-model" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "oytunistrator/olang-language-model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use oytunistrator/olang-language-model with Ollama:
```
ollama run hf.co/oytunistrator/olang-language-model:F16
```
Unsloth Desktop

How to use oytunistrator/olang-language-model with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf oytunistrator/olang-language-model:F16

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": "oytunistrator/olang-language-model:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use oytunistrator/olang-language-model with Docker Model Runner:
```
docker model run hf.co/oytunistrator/olang-language-model:F16
```

Lemonade

How to use oytunistrator/olang-language-model with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull oytunistrator/olang-language-model:F16

Run and chat with the model

lemonade run user.olang-language-model-F16

List all available models

lemonade list

Hermes Agent

How to use oytunistrator/olang-language-model with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf oytunistrator/olang-language-model:F16

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 oytunistrator/olang-language-model:F16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use oytunistrator/olang-language-model with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf oytunistrator/olang-language-model:F16

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 "oytunistrator/olang-language-model:F16" \
  --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"

O Language Programming Model

A programming model specialized for the O Language programming language. Its primary purpose is to turn natural-language requests such as “write this in O Language” into runnable .ola code.

The model analyzes requirements, selects documented O Language syntax, and produces a complete .ola program. It can also explain, debug, and improve existing O Language code.

Capabilities

Create new O Language programs
Explain and improve .ola code
Answer O Language syntax and command questions
Generate examples for files, processes, networking, and system operations
Use O Language documentation while generating code
Convert natural-language requirements into .ola programs
Produce .ola programs, .olm modules, and .olp package files
Solve general programming and debugging requests in the language requested by the user

When a request explicitly names O Language or Olang, the response must use documented O Language syntax. For other programming requests, the requested programming language should be used.

Usage

Ask the model to solve a task in O Language. For code-generation requests, it should return a complete artifact instead of only an explanation.

Example request:

Write an O Language program that asks for a name and prints a greeting.

The canonical minimal example is:

output("Hello, World!")

Validate generated code with the O Language runtime before executing it.

Tool support

The model is designed to work through the agent layer with:

search_docs: search the O Language documentation.
explain_syntax: find usage for an O Language symbol or command.
validate_olang: validate generated .ola code with the O Language runtime.
analyze_olang: analyze likely syntax or runtime problems.
run_olang: run documented run, exec, compile, or info operations.
write_olang_artifact: write an explicitly requested .ola, .olm, or .olp file in the configured workspace.

Tool requests use JSON:

{"tool":"validate_olang","arguments":{"code":"output(\"Hello\")"}}

The model is not only a documentation question-answering bot; it is intended to translate programming requirements into O Language programs, analyze bugs, and propose corrected code.

RAG usage

The model works best with the live RAG index built from the O Language wiki and website documentation:

https://onix-project.com/O_Language

The GGUF file contains model weights only. RAG retrieval and tool execution are provided by the accompanying agent runtime.

Safety and limitations

Generated code must be treated as untrusted output. Run it in a sandbox with restricted network, filesystem, and process access.

When the O Language documentation or runtime changes, rebuild the RAG index and reassess generated answers.

Downloads last month: 20

GGUF

Model size

2B params

Architecture

qwen2

Hardware compatibility

16-bit