Instructions to use wngkdud/Orion-14B-Chat_SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use wngkdud/Orion-14B-Chat_SFT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="wngkdud/Orion-14B-Chat_SFT", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("wngkdud/Orion-14B-Chat_SFT", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use wngkdud/Orion-14B-Chat_SFT with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "wngkdud/Orion-14B-Chat_SFT" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "wngkdud/Orion-14B-Chat_SFT", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/wngkdud/Orion-14B-Chat_SFT
- SGLang
How to use wngkdud/Orion-14B-Chat_SFT 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 "wngkdud/Orion-14B-Chat_SFT" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "wngkdud/Orion-14B-Chat_SFT", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "wngkdud/Orion-14B-Chat_SFT" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "wngkdud/Orion-14B-Chat_SFT", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use wngkdud/Orion-14B-Chat_SFT with Docker Model Runner:
docker model run hf.co/wngkdud/Orion-14B-Chat_SFT
Download model-00003-of-00006.safetensors from wngkdud/Orion-14B-Chat_SFT: direct link, hf CLI and curl.
- Browser
- Download file 4.93 GB
-
https://huggingface.co/wngkdud/Orion-14B-Chat_SFT/resolve/main/model-00003-of-00006.safetensors
- Command line
-
hf download hf://wngkdud/Orion-14B-Chat_SFT/model-00003-of-00006.safetensors
-
curl -L -o model-00003-of-00006.safetensors https://huggingface.co/wngkdud/Orion-14B-Chat_SFT/resolve/main/model-00003-of-00006.safetensors
4.93 GB
- Xet hash:
- aba894d114a3f7b8ba7396f52a30ca5d4ff31872619480df4d0532d073c0b24b
- Size of remote file:
- 4.93 GB
- SHA256:
- 8d7fabf4b758f231da50c32b75dad3bb5a478cf149e04c19bfeeb93aef96200e
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.