Instructions to use dongboklee/gORM-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dongboklee/gORM-8B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="dongboklee/gORM-8B") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("dongboklee/gORM-8B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use dongboklee/gORM-8B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "dongboklee/gORM-8B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dongboklee/gORM-8B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/dongboklee/gORM-8B
- SGLang
How to use dongboklee/gORM-8B 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 "dongboklee/gORM-8B" \ --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": "dongboklee/gORM-8B", "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 "dongboklee/gORM-8B" \ --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": "dongboklee/gORM-8B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use dongboklee/gORM-8B with Docker Model Runner:
docker model run hf.co/dongboklee/gORM-8B
Improve model card with abstract and structural enhancements
#1
by nielsr HF Staff - opened
This PR enhances the model card for gORM-8B by:
- Adding a "Model Overview" section: This new section incorporates the paper's abstract, providing a more comprehensive understanding of the model's context, research findings, and its role as a generative outcome reward model.
- Improving structure: The paper and repository links are now grouped under a dedicated "Paper and Code" section for better readability.
- Retaining existing information: All current metadata, the detailed "Direct Use" code snippet, and the citation information remain unchanged to preserve their accuracy and functionality.
- Adhering to guidelines: The existing arXiv paper link is kept as per the instruction not to replace it with a Hugging Face paper link if an arXiv link is already present.
These changes aim to make the model card more informative and easier to navigate for users on the Hugging Face Hub.