Instructions to use SYNLP/ChiMed-GPT-1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SYNLP/ChiMed-GPT-1.0 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="SYNLP/ChiMed-GPT-1.0")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("SYNLP/ChiMed-GPT-1.0") model = AutoModelForCausalLM.from_pretrained("SYNLP/ChiMed-GPT-1.0") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use SYNLP/ChiMed-GPT-1.0 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "SYNLP/ChiMed-GPT-1.0" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SYNLP/ChiMed-GPT-1.0", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/SYNLP/ChiMed-GPT-1.0
- SGLang
How to use SYNLP/ChiMed-GPT-1.0 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 "SYNLP/ChiMed-GPT-1.0" \ --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": "SYNLP/ChiMed-GPT-1.0", "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 "SYNLP/ChiMed-GPT-1.0" \ --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": "SYNLP/ChiMed-GPT-1.0", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use SYNLP/ChiMed-GPT-1.0 with Docker Model Runner:
docker model run hf.co/SYNLP/ChiMed-GPT-1.0
Could you please redo your model using Zephyr 7b beta as base model instead ?
Hello,
your work is impresive , but we as citizens of the world would like to try and use it and we have a great barrier in the fact that we do not know chinese language :( . Can you please redo your work using as base model Zephyr 7b beta (https://huggingface.co/HuggingFaceH4/zephyr-7b-beta because it was trained as a multilingual model from the start) , and if you can finetune the model with Chinese and English data so that it can be used by people all around the world ?!? Theoretically it should be able to do some zero shot learning and when questioned in other language than the one in which was finetuned to answer in that language .
Thank you.
Catalin Ciocea
Hi Catalin,
Thank you for your interest and valuable suggestion!
We are currently working on a medical LLM for Chinese and English. Stay tuned for more updates!
Best regards,
Yuanhe
Hello Mr. Yuanhe,
thank you for your answer. I'm from Romania. I know well English language , but there are a lot of peoples that does not know it. And usually in the poorest countries where
they also have not enough money to go to a competent doctor or a good hospital . The great thing that an "AI doctor" can do is to allow all to access medical consultation
and knowledge for free or for a fraction of the expenses that they need to make otherways. It is also a great threat to human doctors and medical personal as they can be "replaced" all together by
AI in a foreseable future. The Zephyr model that I suggested to use as base "knows" around 100 languages ...as it's creators said . Ok. Thank you anyway for your great work. You are doing a great job for poor humans that are seek .
Have a good day.
Catalin