Instructions to use Kooten/DaringMaid-13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Kooten/DaringMaid-13B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Kooten/DaringMaid-13B")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("Kooten/DaringMaid-13B") model = AutoModelForMultimodalLM.from_pretrained("Kooten/DaringMaid-13B") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Kooten/DaringMaid-13B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Kooten/DaringMaid-13B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Kooten/DaringMaid-13B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Kooten/DaringMaid-13B
- SGLang
How to use Kooten/DaringMaid-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 "Kooten/DaringMaid-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": "Kooten/DaringMaid-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 "Kooten/DaringMaid-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": "Kooten/DaringMaid-13B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Kooten/DaringMaid-13B with Docker Model Runner:
docker model run hf.co/Kooten/DaringMaid-13B
It Delivers!
This does feel smarter and it follows even the character cards well. Very well, in fact. It's gotta be a favorite of mine. Think you can do the same for Estopia 13b? It's very good at roleplaying and storytelling but it tends to hallucinate. I haven't found a model that improves it.
Thanks, I appreciate it.
I have not had time to test a lot of models recently but I might take a look, I like the idea of it.
What problems have you had with it? They do mention the stopping token is a bit broken from all the merges in it.
Have you tried KatyTheCutie/EstopianMaid-13B?
The problems I've had was logic (For example a character driving my car to get home instead of using his own car.) My presets and settings are the same as what is suggested in the model card. I am trying EstopianMaid. Pretty good model. It has less logical issues (but I know AI in general has this issue) but it's what I expect it be. Thanks for telling me about it.