Instructions to use HelpingAI/MediKAI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HelpingAI/MediKAI with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="HelpingAI/MediKAI")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("HelpingAI/MediKAI") model = AutoModelForCausalLM.from_pretrained("HelpingAI/MediKAI") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use HelpingAI/MediKAI with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "HelpingAI/MediKAI" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "HelpingAI/MediKAI", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/HelpingAI/MediKAI
- SGLang
How to use HelpingAI/MediKAI 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 "HelpingAI/MediKAI" \ --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": "HelpingAI/MediKAI", "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 "HelpingAI/MediKAI" \ --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": "HelpingAI/MediKAI", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use HelpingAI/MediKAI with Docker Model Runner:
docker model run hf.co/HelpingAI/MediKAI
Update README.md
Browse files
README.md
CHANGED
|
@@ -9,17 +9,6 @@ Welcome to mediKAI, the latest healthcare-focused model by HelpingAI designed to
|
|
| 9 |
## Overview
|
| 10 |
mediKAI is a 14 billion parameters model that specializes in healthcare-related topics and medical assistance. Whether you have questions about symptoms, treatments, medications, or general health and wellness, mediKAI is here to help.
|
| 11 |
|
| 12 |
-
## Features
|
| 13 |
-
- Deep understanding of healthcare topics
|
| 14 |
-
- Multilingual support in English, Chinese, French, Hindi, Spanish, and Arabic
|
| 15 |
-
- Accurate information, guidance, and advice on medical queries
|
| 16 |
-
- Reliable and insightful responses to healthcare inquiries
|
| 17 |
-
|
| 18 |
-
## Usage
|
| 19 |
-
1. Simply input your healthcare-related query in one of the supported languages.
|
| 20 |
-
2. Receive accurate information and assistance from mediKAI.
|
| 21 |
-
3. Stay informed about your health and wellness with mediKAI as your healthcare companion.
|
| 22 |
-
|
| 23 |
## Languages Supported
|
| 24 |
- English
|
| 25 |
- French
|
|
|
|
| 9 |
## Overview
|
| 10 |
mediKAI is a 14 billion parameters model that specializes in healthcare-related topics and medical assistance. Whether you have questions about symptoms, treatments, medications, or general health and wellness, mediKAI is here to help.
|
| 11 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
## Languages Supported
|
| 13 |
- English
|
| 14 |
- French
|