Instructions to use LoneStriker/Orca-2-13b-6.0bpw-h6-exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LoneStriker/Orca-2-13b-6.0bpw-h6-exl2 with Transformers:

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

pipe = pipeline("text-generation", model="LoneStriker/Orca-2-13b-6.0bpw-h6-exl2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LoneStriker/Orca-2-13b-6.0bpw-h6-exl2")
model = AutoModelForCausalLM.from_pretrained("LoneStriker/Orca-2-13b-6.0bpw-h6-exl2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LoneStriker/Orca-2-13b-6.0bpw-h6-exl2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LoneStriker/Orca-2-13b-6.0bpw-h6-exl2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LoneStriker/Orca-2-13b-6.0bpw-h6-exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/LoneStriker/Orca-2-13b-6.0bpw-h6-exl2

SGLang

How to use LoneStriker/Orca-2-13b-6.0bpw-h6-exl2 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 "LoneStriker/Orca-2-13b-6.0bpw-h6-exl2" \
    --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": "LoneStriker/Orca-2-13b-6.0bpw-h6-exl2",
		"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 "LoneStriker/Orca-2-13b-6.0bpw-h6-exl2" \
        --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": "LoneStriker/Orca-2-13b-6.0bpw-h6-exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use LoneStriker/Orca-2-13b-6.0bpw-h6-exl2 with Docker Model Runner:
```
docker model run hf.co/LoneStriker/Orca-2-13b-6.0bpw-h6-exl2
```

Orca-2-13b-6.0bpw-h6-exl2 / huggingface-metadata.txt

LoneStriker

Upload folder using huggingface_hub

5f18fc2 over 2 years ago

Raw

History Blame Contribute Delete

805 Bytes

	url: https://huggingface.co/microsoft/Orca-2-13b
	branch: main
	download date: 2023-11-20 21:44:37
	sha256sum:
	48b50d9d6ef77522b210c62ec214dd01295fcf88a3160acce32cae23d033ce1d pytorch_model-00001-of-00006.bin
	d5dec51a499eea69793a89ce4409b019092829a8efbe5ca0f73cd1da3b7431d3 pytorch_model-00002-of-00006.bin
	5bd111371970c260e3b38685f6a39bc54ba189e9aa1297e142b9193e21fab415 pytorch_model-00003-of-00006.bin
	9870c5705b3b409ba7ee8c60c6e785c350d8f69194ea58db11a8acfef808a4cf pytorch_model-00004-of-00006.bin
	e17d513a94757fed6a86e48d9f425fcf0a52f8bc47b83f84e809eabc5e685196 pytorch_model-00005-of-00006.bin
	974119123f7033984e573b0d2c9754275bd448c688a09488e52f2f44206785e1 pytorch_model-00006-of-00006.bin
	9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 tokenizer.model