Instructions to use OrionStarAI/Orion-14B-Chat-RAG with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OrionStarAI/Orion-14B-Chat-RAG with Transformers:

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

pipe = pipeline("text-generation", model="OrionStarAI/Orion-14B-Chat-RAG", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("OrionStarAI/Orion-14B-Chat-RAG", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OrionStarAI/Orion-14B-Chat-RAG with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OrionStarAI/Orion-14B-Chat-RAG"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OrionStarAI/Orion-14B-Chat-RAG",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OrionStarAI/Orion-14B-Chat-RAG

SGLang

How to use OrionStarAI/Orion-14B-Chat-RAG 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 "OrionStarAI/Orion-14B-Chat-RAG" \
    --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": "OrionStarAI/Orion-14B-Chat-RAG",
		"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 "OrionStarAI/Orion-14B-Chat-RAG" \
        --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": "OrionStarAI/Orion-14B-Chat-RAG",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OrionStarAI/Orion-14B-Chat-RAG with Docker Model Runner:
```
docker model run hf.co/OrionStarAI/Orion-14B-Chat-RAG
```

Orion-14B-Chat-RAG

Commit History

Update README_ko.md

305d09c
verified

renillhuang commited on Mar 26, 2024

Update README_ja.md

5829290
verified

renillhuang commited on Mar 26, 2024

Update README_zh.md

78494f0
verified

renillhuang commited on Mar 26, 2024

Update README.md

4c0fa33
verified

renillhuang commited on Mar 26, 2024

Update Wechat group QR code.

6cb8d2c
verified

renillhuang commited on Mar 3, 2024

Update tokenization_orion.py

f9cd51e
verified

liuyongq commited on Jan 31, 2024

Update README_zh.md

7439953
verified

liuyongq commited on Jan 26, 2024

Update README.md

87ffe08
verified

liuyongq commited on Jan 26, 2024

Update README_ko.md

66ff7b2
verified

renillhuang commited on Jan 26, 2024

Update README_ja.md

7b33ad4
verified

renillhuang commited on Jan 26, 2024

Update README_zh.md

c0dd85a
verified

renillhuang commited on Jan 26, 2024

Update README.md

2a5b79b
verified

renillhuang commited on Jan 26, 2024