Instructions to use ddh0/OrcaMaid-13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ddh0/OrcaMaid-13b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ddh0/OrcaMaid-13b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("ddh0/OrcaMaid-13b") model = AutoModelForCausalLM.from_pretrained("ddh0/OrcaMaid-13b") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use ddh0/OrcaMaid-13b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ddh0/OrcaMaid-13b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ddh0/OrcaMaid-13b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ddh0/OrcaMaid-13b
- SGLang
How to use ddh0/OrcaMaid-13b 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 "ddh0/OrcaMaid-13b" \ --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": "ddh0/OrcaMaid-13b", "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 "ddh0/OrcaMaid-13b" \ --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": "ddh0/OrcaMaid-13b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ddh0/OrcaMaid-13b with Docker Model Runner:
docker model run hf.co/ddh0/OrcaMaid-13b
Thanks for making this model!
From the RP testing I’ve done, it’s very, very good. Easily within the top 5% of models I’ve tried. It’s got a few issues with logic that I’ve seen. But, otherwise, it does a very convincing RP that’s, IMO, better than tiefighter.
you're welcome, and thank you! i'm curious to know what you think about the newer orcamaid versions in comparison, if you've tried them
I’ve got them in my ‘to try’ list. Just waiting for TheBloke or someone to do a GGUF quantize of it. I’m definitely looking forward to trying it.
I submitted a request for both of them today, so I'm guessing they'll be up tomorrow 🤞