Instructions to use Open-Orca/OpenOrca with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Open-Orca/OpenOrca with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Open-Orca/OpenOrca")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Open-Orca/OpenOrca") model = AutoModelForCausalLM.from_pretrained("Open-Orca/OpenOrca") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Open-Orca/OpenOrca with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Open-Orca/OpenOrca" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Open-Orca/OpenOrca", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Open-Orca/OpenOrca
- SGLang
How to use Open-Orca/OpenOrca 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 "Open-Orca/OpenOrca" \ --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": "Open-Orca/OpenOrca", "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 "Open-Orca/OpenOrca" \ --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": "Open-Orca/OpenOrca", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Open-Orca/OpenOrca with Docker Model Runner:
docker model run hf.co/Open-Orca/OpenOrca
Update README.md
Browse files
README.md
CHANGED
|
@@ -72,13 +72,21 @@ We trained for 4 epochs and selected a snapshot at 3 epochs for peak performance
|
|
| 72 |
|
| 73 |
Please await our full releases for further training details.
|
| 74 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 75 |
|
| 76 |
# Citation
|
| 77 |
|
| 78 |
```bibtex
|
| 79 |
@software{OpenOrca_Preview1,
|
| 80 |
title = {OpenOrca_Preview1: A LLaMA-13B Model Fine-tuned on Small Portion of OpenOrcaV1 Dataset},
|
| 81 |
-
author = {Wing Lian and Bleys Goodson and Eugene Pentland and Austin Cook and Chanvichet Vong
|
| 82 |
year = {2023},
|
| 83 |
publisher = {HuggingFace},
|
| 84 |
journal = {HuggingFace repository},
|
|
|
|
| 72 |
|
| 73 |
Please await our full releases for further training details.
|
| 74 |
|
| 75 |
+
# Prompting
|
| 76 |
+
|
| 77 |
+
It uses the Alpaca format (see [FastChat implementation example](https://github.com/lm-sys/FastChat/blob/daa2b9abe20597ebf34dc5df164d450456610c74/fastchat/conversation.py#L198-L229)):
|
| 78 |
+
```
|
| 79 |
+
### Instruction:
|
| 80 |
+
|
| 81 |
+
### Response:
|
| 82 |
+
```
|
| 83 |
|
| 84 |
# Citation
|
| 85 |
|
| 86 |
```bibtex
|
| 87 |
@software{OpenOrca_Preview1,
|
| 88 |
title = {OpenOrca_Preview1: A LLaMA-13B Model Fine-tuned on Small Portion of OpenOrcaV1 Dataset},
|
| 89 |
+
author = {Wing Lian and Bleys Goodson and Eugene Pentland and Austin Cook and Chanvichet Vong and "Teknium"},
|
| 90 |
year = {2023},
|
| 91 |
publisher = {HuggingFace},
|
| 92 |
journal = {HuggingFace repository},
|