Instructions to use Undi95/CreativityEngine with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Undi95/CreativityEngine with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Undi95/CreativityEngine")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Undi95/CreativityEngine")
model = AutoModelForCausalLM.from_pretrained("Undi95/CreativityEngine")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Undi95/CreativityEngine with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Undi95/CreativityEngine"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Undi95/CreativityEngine",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Undi95/CreativityEngine

SGLang

How to use Undi95/CreativityEngine 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/CreativityEngine" \
    --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/CreativityEngine",
		"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/CreativityEngine" \
        --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/CreativityEngine",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Undi95/CreativityEngine with Docker Model Runner:
```
docker model run hf.co/Undi95/CreativityEngine
```

CreativityEngine / README.md

Undi95

Adding Evaluation Results (#2)

472065e over 2 years ago

preview code

raw

history blame contribute delete

840 Bytes

	---
	license: cc-by-nc-4.0
	---
	https://huggingface.co/jondurbin/airoboros-lmoe-13b-2.1/tree/main/adapters/creative + https://huggingface.co/elinas/chronos-13b-v2 weight: 0.38

	For Dampf
	# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
	Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Undi95__CreativityEngine)

	\| Metric \| Value \|
	\|-----------------------\|---------------------------\|
	\| Avg. \| 52.07 \|
	\| ARC (25-shot) \| 59.3 \|
	\| HellaSwag (10-shot) \| 82.42 \|
	\| MMLU (5-shot) \| 53.55 \|
	\| TruthfulQA (0-shot) \| 52.46 \|
	\| Winogrande (5-shot) \| 74.19 \|
	\| GSM8K (5-shot) \| 9.55 \|
	\| DROP (3-shot) \| 32.98 \|

	---
	license: cc-by-nc-4.0
	---
	https://huggingface.co/jondurbin/airoboros-lmoe-13b-2.1/tree/main/adapters/creative + https://huggingface.co/elinas/chronos-13b-v2 weight: 0.38

	For Dampf
	# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
	Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Undi95__CreativityEngine)

	\| Metric \| Value \|
	\|-----------------------\|---------------------------\|
	\| Avg. \| 52.07 \|
	\| ARC (25-shot) \| 59.3 \|
	\| HellaSwag (10-shot) \| 82.42 \|
	\| MMLU (5-shot) \| 53.55 \|
	\| TruthfulQA (0-shot) \| 52.46 \|
	\| Winogrande (5-shot) \| 74.19 \|
	\| GSM8K (5-shot) \| 9.55 \|
	\| DROP (3-shot) \| 32.98 \|