Instructions to use Undi95/LewdEngine with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Undi95/LewdEngine with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Undi95/LewdEngine")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Undi95/LewdEngine") model = AutoModelForCausalLM.from_pretrained("Undi95/LewdEngine") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Undi95/LewdEngine with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Undi95/LewdEngine" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Undi95/LewdEngine", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Undi95/LewdEngine
- SGLang
How to use Undi95/LewdEngine 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 "Undi95/LewdEngine" \ --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": "Undi95/LewdEngine", "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 "Undi95/LewdEngine" \ --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": "Undi95/LewdEngine", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Undi95/LewdEngine with Docker Model Runner:
docker model run hf.co/Undi95/LewdEngine
https://huggingface.co/KoboldAI/LLaMA2-13B-Holomax + https://huggingface.co/nRuaif/Kimiko-v2-13B lora weight: 0.27
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 47.92 |
| ARC (25-shot) | 60.49 |
| HellaSwag (10-shot) | 83.08 |
| MMLU (5-shot) | 54.84 |
| TruthfulQA (0-shot) | 43.63 |
| Winogrande (5-shot) | 74.9 |
| GSM8K (5-shot) | 12.36 |
| DROP (3-shot) | 6.17 |
- Downloads last month
- 1,033