Instructions to use OpenRussianAI/OpenAirAI-X with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenRussianAI/OpenAirAI-X with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="OpenRussianAI/OpenAirAI-X")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("OpenRussianAI/OpenAirAI-X") model = AutoModelForCausalLM.from_pretrained("OpenRussianAI/OpenAirAI-X", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use OpenRussianAI/OpenAirAI-X 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 OpenRussianAI/OpenAirAI-X # Run inference directly in the terminal: llama cli -hf OpenRussianAI/OpenAirAI-X
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf OpenRussianAI/OpenAirAI-X # Run inference directly in the terminal: llama cli -hf OpenRussianAI/OpenAirAI-X
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 OpenRussianAI/OpenAirAI-X # Run inference directly in the terminal: ./llama-cli -hf OpenRussianAI/OpenAirAI-X
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 OpenRussianAI/OpenAirAI-X # Run inference directly in the terminal: ./build/bin/llama-cli -hf OpenRussianAI/OpenAirAI-X
Use Docker
docker model run hf.co/OpenRussianAI/OpenAirAI-X
- LM Studio
- Jan
- vLLM
How to use OpenRussianAI/OpenAirAI-X with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "OpenRussianAI/OpenAirAI-X" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "OpenRussianAI/OpenAirAI-X", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/OpenRussianAI/OpenAirAI-X
- SGLang
How to use OpenRussianAI/OpenAirAI-X 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 "OpenRussianAI/OpenAirAI-X" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "OpenRussianAI/OpenAirAI-X", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "OpenRussianAI/OpenAirAI-X" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "OpenRussianAI/OpenAirAI-X", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Ollama
How to use OpenRussianAI/OpenAirAI-X with Ollama:
ollama run hf.co/OpenRussianAI/OpenAirAI-X
- Unsloth Desktop
- Docker Model Runner
How to use OpenRussianAI/OpenAirAI-X with Docker Model Runner:
docker model run hf.co/OpenRussianAI/OpenAirAI-X
- Lemonade
How to use OpenRussianAI/OpenAirAI-X with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull OpenRussianAI/OpenAirAI-X
Run and chat with the model
lemonade run user.OpenAirAI-X-{{QUANT_TAG}}List all available models
lemonade list
- Atomic Chat
Commit History
Update README.md 031addc verified
X commited on
Create LICENSE 2cff8da verified
X commited on
Create README.md 75d75de verified
X commited on
feat: Add ONNX model and external data weights 4564344 verified
X commited on
Update .gitattributes cff1541 verified
X commited on
feat: Add GGUF model created by X_BFDI & RootLinux21 49b1bf9 verified
X commited on
feat: Spelling Fix v20 e68407b verified
X commited on
feat: Name Precision v19 5848b62 verified
X commited on
feat: Facts about OpenRussianAI v18 9dd074f verified
X commited on
feat: Smart Context v16 b467ccc verified
X commited on
feat: v15 75b51ee verified
X commited on
feat: Anti-loop v12 104dbb7 verified
X commited on
feat: Final OpenAirAI-Bear-2026 f3bb42f verified
X commited on
feat: Identity Override OpenAirAI-Bear-2026 v11 ce097ea verified
X commited on
feat: Pure Identity OpenAirAI-Bear-2026 v10 578d52a verified
X commited on
feat: Name-Locked OpenAirAI-Bear-2026 v8 a2d9d00 verified
X commited on
feat: Anti-hallucination OpenAirAI-Bear-2026 6e9a19f verified
X commited on
feat: Anti-hallucination OpenAirAI-Bear-2026 b6506df verified
X commited on
feat: Anti-hallucination OpenAirAI-Bear-2026 305e9c5 verified
X commited on
feat: Final OpenAirAI-Bear-2026 b67eb1e verified
X commited on
feat: OpenAirAI v3 with 200 stable dialogues 9764d97 verified
X commited on
feat: Final Clean OpenAirAI-Bear-2026 e049a66 verified
X commited on
feat: Stable OpenAirAI with extended dialogue dataset b4a8dd3 verified
X commited on
feat: Stable OpenAirAI-Bear-2026 cc15ed3 verified
X commited on
feat: Initial upload of OpenAirAI-Bear-2026 fcf5696 verified
X commited on
feat: Upload OpenAirAI-Bear-2026 with Safetensors 67e672f verified
X commited on
Delete vocab.json with huggingface_hub 514d708 verified
X commited on
Delete model.safetensors with huggingface_hub 47e5635 verified
X commited on
Delete config.json with huggingface_hub 6f3d357 verified
X commited on
Delete .gitattributes with huggingface_hub 41ac0c6 verified
X commited on
Upload vocab.json with huggingface_hub 97a7f44 verified
X commited on
Upload model.safetensors with huggingface_hub 29850ee verified
X commited on
Upload config.json with huggingface_hub 0aab12d verified
X commited on
Delete vocab.json with huggingface_hub 6e56715 verified
X commited on
Delete tokenizer_config.json with huggingface_hub b3a5192 verified
X commited on
Delete tokenizer.json with huggingface_hub 31abaa9 verified
X commited on
Delete model.safetensors with huggingface_hub 98005bc verified
X commited on
Delete generation_config.json with huggingface_hub 75df0e8 verified
X commited on
Delete config.json with huggingface_hub 3e63132 verified
X commited on
Delete README.md with huggingface_hub 1506996 verified
X commited on
Delete .gitattributes with huggingface_hub 018ad19 verified
X commited on
Upload tokenizer 8e3f445 verified
X commited on
Реальный GPT-2 трансформер, дообученный на диалогах e53f148 verified
X commited on
Upload vocab.json with huggingface_hub a3102b7 verified
X commited on
Upload model.safetensors with huggingface_hub 1033890 verified
X commited on
Delete vocab.json with huggingface_hub 841bd46 verified
X commited on
Delete model.safetensors with huggingface_hub 3114da4 verified
X commited on
Delete README.md with huggingface_hub 27cd319 verified
X commited on
Delete .gitattributes with huggingface_hub 29bdc73 verified
X commited on