Instructions to use dongbobo/MyAwesomeModel with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dongbobo/MyAwesomeModel with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="dongbobo/MyAwesomeModel")# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("dongbobo/MyAwesomeModel", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use dongbobo/MyAwesomeModel with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "dongbobo/MyAwesomeModel" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dongbobo/MyAwesomeModel", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/dongbobo/MyAwesomeModel
- SGLang
How to use dongbobo/MyAwesomeModel 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 "dongbobo/MyAwesomeModel" \ --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": "dongbobo/MyAwesomeModel", "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 "dongbobo/MyAwesomeModel" \ --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": "dongbobo/MyAwesomeModel", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use dongbobo/MyAwesomeModel with Docker Model Runner:
docker model run hf.co/dongbobo/MyAwesomeModel
| import argparse | |
| import os | |
| import sys | |
| # Add parent directory to path to import utils | |
| sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', '..')) | |
| from utils.benchmark_utils import get_benchmark_score | |
| def main(): | |
| parser = argparse.ArgumentParser(description="Evaluate summarization") | |
| parser.add_argument("model_path", type=str, help="Path to model checkpoint") | |
| args = parser.parse_args() | |
| if not os.path.isdir(args.model_path): | |
| print(f"Error: Directory not found at '{args.model_path}'", file=sys.stderr) | |
| sys.exit(1) | |
| checkpoint_name = os.path.basename(os.path.normpath(args.model_path)) | |
| try: | |
| step_number = int(checkpoint_name.split('_')[-1]) | |
| except (ValueError, IndexError): | |
| print(f"Error: Cannot parse step number from '{checkpoint_name}'", file=sys.stderr) | |
| sys.exit(1) | |
| result = get_benchmark_score("summarization", step_number) | |
| if result is None: | |
| print(f"Error: Invalid step number {step_number}", file=sys.stderr) | |
| sys.exit(1) | |
| print(result) | |
| if __name__ == "__main__": | |
| main() | |