Instructions to use nold/MediKAI-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nold/MediKAI-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="nold/MediKAI-GGUF",
	filename="MediKAI_Q3_K_M.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use nold/MediKAI-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf nold/MediKAI-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf nold/MediKAI-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf nold/MediKAI-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf nold/MediKAI-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf nold/MediKAI-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf nold/MediKAI-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf nold/MediKAI-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf nold/MediKAI-GGUF:Q4_K_M

Use Docker

docker model run hf.co/nold/MediKAI-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use nold/MediKAI-GGUF with Ollama:
```
ollama run hf.co/nold/MediKAI-GGUF:Q4_K_M
```

Unsloth Studio

How to use nold/MediKAI-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for nold/MediKAI-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for nold/MediKAI-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for nold/MediKAI-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use nold/MediKAI-GGUF with Docker Model Runner:
```
docker model run hf.co/nold/MediKAI-GGUF:Q4_K_M
```

Lemonade

How to use nold/MediKAI-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nold/MediKAI-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.MediKAI-GGUF-Q4_K_M

List all available models

lemonade list

MediKAI - Your Healthcare Companion 🏥💬

Welcome to mediKAI, the latest healthcare-focused model by HelpingAI designed to provide personalized assistance and support in medical-related queries.

Overview

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.

Languages Supported

English
French
Hindi
Spanish
Arabic


***

Quantization of Model [OEvortex/MediKAI](https://huggingface.co/OEvortex/MediKAI).
Created using [llm-quantizer](https://github.com/Nold360/llm-quantizer) Pipeline

Downloads last month: 31

GGUF

Model size

14B params

Architecture

gemma

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support