Instructions to use lil-lab/respect with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lil-lab/respect with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="lil-lab/respect")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("lil-lab/respect", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use lil-lab/respect with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "lil-lab/respect" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "lil-lab/respect", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/lil-lab/respect
- SGLang
How to use lil-lab/respect 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 "lil-lab/respect" \ --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": "lil-lab/respect", "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 "lil-lab/respect" \ --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": "lil-lab/respect", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use lil-lab/respect with Docker Model Runner:
docker model run hf.co/lil-lab/respect
Improve model card: Add paper link, pipeline tag, library name, links, and usage
#1
by nielsr HF Staff - opened
This PR significantly enhances the model card for the lil-lab/respect model by:
- Updating the paper reference to the official Hugging Face paper: The Era of Real-World Human Interaction: RL from User Conversations.
- Adding
pipeline_tag: image-text-to-textfor improved discoverability on the Hub. - Specifying
library_name: transformersbased on the explicit usage of thetransformerslibrary in the GitHub README. - Including direct links to the project page and GitHub repository.
- Providing a concise overview of the model based on the paper abstract.
- Adding a comprehensive sample usage section, including environment setup, data download, and model loading, directly from the GitHub README.
Hi Niels, thanks for the addition - I am happy to merge and to make it more useful for the HF community.
Everything looks good, though the paper link should be https://huggingface.co/papers/2410.13852 from last year under a different title
Feel free to merge and adapt
chenzizhao changed pull request status to merged