Instructions to use thillaic/MediQuill with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use thillaic/MediQuill with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="thillaic/MediQuill")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("thillaic/MediQuill") model = AutoModelForCausalLM.from_pretrained("thillaic/MediQuill", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use thillaic/MediQuill with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "thillaic/MediQuill" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "thillaic/MediQuill", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/thillaic/MediQuill
- SGLang
How to use thillaic/MediQuill 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 "thillaic/MediQuill" \ --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": "thillaic/MediQuill", "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 "thillaic/MediQuill" \ --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": "thillaic/MediQuill", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use thillaic/MediQuill with Docker Model Runner:
docker model run hf.co/thillaic/MediQuill
| license: mit | |
| language: | |
| - en | |
| library_name: transformers | |
| tags: | |
| - medical | |
| datasets: | |
| - thillaic/MedQuad-MedicalQnADataset-Llama2-1k | |
| # Model Card for thillaic/MediQuill | |
| This is a medicine-focussed Llama-2 fine tuned using thillaic/MedQuad-MedicalQnADataset-Llama2-1k dataset | |
| ## Model Details | |
| ### Model Description | |
| The llama-2 model is finetuned with the given dataset to comprehend and respond to diverse medical questions, covering diagnoses, treatments, symptoms, medications, and more | |
| - **Developed by:** [ThillaiC](https://huggingface.co/thillaic) | |
| - **Shared by :** [ThillaiC](https://huggingface.co/thillaic) | |
| - **Model type:** Llama-2 Fine-Tune | |
| - **Language(s) (NLP):** English | |
| - **License:** MIT2.0 | |
| - **Finetuned from model :** [NousResearch/Llama-2-7b-chat-hf](https://huggingface.co/NousResearch/Llama-2-7b-chat-hf) | |
| ### Model Sources | |
| - **Repository:** [thillaic/MediQuill](https://huggingface.co/thillaic/MediQuill) | |
| - **Code :** [github](https://github.com/thillai-c/MediQuill-llama2) | |
| ## Uses | |
| This model aims to provide accurate, up-to-date information and assist healthcare professionals and individuals in making informed decisions about health concerns. | |
| #### Hardware | |
| T4 GPU | |
| ## Model Card Authors [optional] | |
| [ThillaiC](https://huggingface.co/thillaic) | |
| ## Model Card Contact | |
| [ThillaiC](https://huggingface.co/thillaic) |