Instructions to use openchat/openchat_3.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openchat/openchat_3.5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="openchat/openchat_3.5")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("openchat/openchat_3.5", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use openchat/openchat_3.5 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "openchat/openchat_3.5" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "openchat/openchat_3.5", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/openchat/openchat_3.5
- SGLang
How to use openchat/openchat_3.5 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 "openchat/openchat_3.5" \ --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": "openchat/openchat_3.5", "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 "openchat/openchat_3.5" \ --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": "openchat/openchat_3.5", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use openchat/openchat_3.5 with Docker Model Runner:
docker model run hf.co/openchat/openchat_3.5
Request for Model Sharding of OpenChat 3.5 for Improved Accessibility
Hello OpenChat Team,
I hope this message finds you well. I am reaching out to express my appreciation for the OpenChat 3.5 model and to discuss a suggestion that could potentially extend its reach and usability.
One of the challenges I have encountered is the limitation posed by hardware requirements, which can be a barrier for individuals or researchers with access to only lower-end computers. To address this, I am interested in exploring the possibility of model sharding for OpenChat 3.5.
Sharding the model could democratize access, allowing users with less powerful hardware to experiment with and benefit from the model's capabilities. This approach could also optimize the use of the model on popular cloud platforms like Google Colab and Kaggle, which are essential tools for many in the AI community.
The technical intricacies of model sharding notwithstanding, its implementation could lead to broader adoption and spur innovation by enabling a wider audience to work with OpenChat 3.5.
I would love to hear your thoughts on this proposal or any alternative solutions that could help mitigate the hardware constraints faced by many users.
Thank you for your contributions to the field and for considering this enhancement.
+1
A free colab notebook tutorial on how to run the model will be amazing :)