Instructions to use Vortex5/LunaMaid-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Vortex5/LunaMaid-12B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Vortex5/LunaMaid-12B")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("Vortex5/LunaMaid-12B") model = AutoModelForMultimodalLM.from_pretrained("Vortex5/LunaMaid-12B") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Vortex5/LunaMaid-12B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Vortex5/LunaMaid-12B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Vortex5/LunaMaid-12B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Vortex5/LunaMaid-12B
- SGLang
How to use Vortex5/LunaMaid-12B 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 "Vortex5/LunaMaid-12B" \ --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": "Vortex5/LunaMaid-12B", "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 "Vortex5/LunaMaid-12B" \ --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": "Vortex5/LunaMaid-12B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Vortex5/LunaMaid-12B with Docker Model Runner:
docker model run hf.co/Vortex5/LunaMaid-12B
| base_model: | |
| - Vortex5/Moonlit-Shadow-12B | |
| - yamatazen/NeonMaid-12B-v2 | |
| - Vortex5/Vermilion-Sage-12B | |
| library_name: transformers | |
| tags: | |
| - mergekit | |
| - merge | |
| - roleplay | |
|  | |
| # 🩵 LunaMaid-12B | |
| This is a multi-stage merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). | |
| ## 🧬 Merge Overview | |
| **LunaMaid-12B** was produced through a **two-stage multi-model merge** using [MergeKit](https://github.com/arcee-ai/mergekit). | |
| Each stage fuses models with complementary linguistic and stylistic traits to create a cohesive, emotionally nuanced personality. | |
| ### 🩵 **Stage 1 — Slerp Merge (Intermediate Model `First`)** | |
| - **Base Model:** [Vortex5/Vermilion-Sage-12B](https://huggingface.co/Vortex5/Vermilion-Sage-12B) | |
| - **Merged With:** [yamatazen/NeonMaid-12B-v2](https://huggingface.co/yamatazen/NeonMaid-12B-v2) | |
| - **Method:** Spherical Linear Interpolation (Slerp) | |
| <details> | |
| <summary><b>Stage 1 Configuration</b></summary> | |
| ```yaml | |
| name: First | |
| base_model: Vortex5/Vermilion-Sage-12B | |
| models: | |
| - model: yamatazen/NeonMaid-12B-v2 | |
| merge_method: slerp | |
| dtype: bfloat16 | |
| parameters: | |
| normalize: true | |
| t: [0.25, 0.35, 0.45, 0.55, 0.65, 0.75, 0.6, 0.5, 0.6, 0.6] | |
| ``` | |
| </details> | |
| ### 🌑 **Merge Method — Karcher Mean Merge (Final Model)** | |
| - **Base Model:** Intermediate output from Stage 1 `./intermediates/First` | |
| - **Merged With:** [Vortex5/Moonlit-Shadow-12B](https://huggingface.co/Vortex5/Moonlit-Shadow-12B) | |
| - **Method:** [Karcher Mean](https://en.wikipedia.org/wiki/Karcher_mean) (Riemannian Barycenter) | |
| <details> | |
| <summary><b>Stage 2 Configuration</b></summary> | |
| ```yaml | |
| dtype: bfloat16 | |
| merge_method: karcher | |
| modules: | |
| default: | |
| slices: | |
| - sources: | |
| - layer_range: [0, 40] | |
| model: ./intermediates/First | |
| - layer_range: [0, 40] | |
| model: Vortex5/Moonlit-Shadow-12B | |
| parameters: | |
| max_iter: 9999 | |
| tol: 1e-9 | |
| ``` | |
| </details> | |
| ### Models Merged | |
| The following models were included in the merge: | |
| * [Vortex5/Moonlit-Shadow-12B](https://huggingface.co/Vortex5/Moonlit-Shadow-12B) | |
| * [Vortex5/Vermilion-Sage-12B](https://huggingface.co/Vortex5/Vermilion-Sage-12B) | |
| * [yamatazen/NeonMaid-12B-v2](https://huggingface.co/yamatazen/NeonMaid-12B-v2) | |
| * ./intermediates/First | |