Text Generation
Transformers
Safetensors
English
qwen2
nvidia
math
conversational
text-generation-inference
Instructions to use nvidia/OpenMath-Nemotron-14B-Kaggle with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/OpenMath-Nemotron-14B-Kaggle with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="nvidia/OpenMath-Nemotron-14B-Kaggle") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("nvidia/OpenMath-Nemotron-14B-Kaggle") model = AutoModelForCausalLM.from_pretrained("nvidia/OpenMath-Nemotron-14B-Kaggle") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use nvidia/OpenMath-Nemotron-14B-Kaggle with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "nvidia/OpenMath-Nemotron-14B-Kaggle" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "nvidia/OpenMath-Nemotron-14B-Kaggle", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/nvidia/OpenMath-Nemotron-14B-Kaggle
- SGLang
How to use nvidia/OpenMath-Nemotron-14B-Kaggle 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 "nvidia/OpenMath-Nemotron-14B-Kaggle" \ --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": "nvidia/OpenMath-Nemotron-14B-Kaggle", "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 "nvidia/OpenMath-Nemotron-14B-Kaggle" \ --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": "nvidia/OpenMath-Nemotron-14B-Kaggle", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use nvidia/OpenMath-Nemotron-14B-Kaggle with Docker Model Runner:
docker model run hf.co/nvidia/OpenMath-Nemotron-14B-Kaggle
| import json | |
| import logging | |
| from http.server import HTTPServer, BaseHTTPRequestHandler | |
| from handler import EndpointHandler | |
| # Configure logging | |
| logging.basicConfig(level=logging.INFO) | |
| logger = logging.getLogger(__name__) | |
| # Initialize the handler | |
| handler = EndpointHandler() | |
| class RequestHandler(BaseHTTPRequestHandler): | |
| def do_POST(self): | |
| try: | |
| content_length = int(self.headers['Content-Length']) | |
| post_data = self.rfile.read(content_length) | |
| data = json.loads(post_data.decode('utf-8')) | |
| logger.info(f'Received request with {len(data.get("inputs", []))} inputs') | |
| # Process the request | |
| result = handler(data) | |
| # Send response | |
| self.send_response(200) | |
| self.send_header('Content-Type', 'application/json') | |
| self.end_headers() | |
| self.wfile.write(json.dumps(result).encode('utf-8')) | |
| except Exception as e: | |
| logger.error(f'Error processing request: {str(e)}') | |
| self.send_response(500) | |
| self.send_header('Content-Type', 'application/json') | |
| self.end_headers() | |
| error_response = [{'error': str(e), 'generated_text': ''}] | |
| self.wfile.write(json.dumps(error_response).encode('utf-8')) | |
| def do_GET(self): | |
| if self.path == '/health': | |
| # Trigger initialisation if needed but don't block. | |
| if not handler.initialized: | |
| try: | |
| handler._initialize_components() | |
| except Exception as e: | |
| logger.error(f'Initialization failed during health check: {str(e)}') | |
| is_ready = handler.initialized | |
| health_response = { | |
| 'status': 'healthy' if is_ready else 'unhealthy', | |
| 'model_ready': is_ready | |
| } | |
| try: | |
| self.send_response(200 if is_ready else 503) | |
| self.send_header('Content-Type', 'application/json') | |
| self.end_headers() | |
| self.wfile.write(json.dumps(health_response).encode('utf-8')) | |
| except BrokenPipeError: | |
| # Client disconnected before we replied – safe to ignore. | |
| pass | |
| return | |
| else: | |
| self.send_response(404) | |
| self.end_headers() | |
| def log_message(self, format, *args): | |
| # Suppress default HTTP server logs to keep output clean | |
| pass | |
| if __name__ == "__main__": | |
| server = HTTPServer(('0.0.0.0', 80), RequestHandler) | |
| logger.info('HTTP server started on port 80') | |
| server.serve_forever() |