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
Commit ·
8e1ece7
1
Parent(s): ae8fb45
Adding Evaluation Results (#2)
Browse files- Adding Evaluation Results (a8693c3e180435fba4c31c3c50cb0d3913a5e0fa)
Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -1,4 +1,17 @@
|
|
| 1 |
---
|
| 2 |
license: cc-by-nc-4.0
|
| 3 |
---
|
| 4 |
-
https://huggingface.co/KoboldAI/LLaMA2-13B-Holomax + https://huggingface.co/nRuaif/Kimiko-v2-13B lora weight: 0.27
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: cc-by-nc-4.0
|
| 3 |
---
|
| 4 |
+
https://huggingface.co/KoboldAI/LLaMA2-13B-Holomax + https://huggingface.co/nRuaif/Kimiko-v2-13B lora weight: 0.27
|
| 5 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 6 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Undi95__LewdEngine)
|
| 7 |
+
|
| 8 |
+
| Metric | Value |
|
| 9 |
+
|-----------------------|---------------------------|
|
| 10 |
+
| Avg. | 47.92 |
|
| 11 |
+
| ARC (25-shot) | 60.49 |
|
| 12 |
+
| HellaSwag (10-shot) | 83.08 |
|
| 13 |
+
| MMLU (5-shot) | 54.84 |
|
| 14 |
+
| TruthfulQA (0-shot) | 43.63 |
|
| 15 |
+
| Winogrande (5-shot) | 74.9 |
|
| 16 |
+
| GSM8K (5-shot) | 12.36 |
|
| 17 |
+
| DROP (3-shot) | 6.17 |
|