Instructions to use Faris-Faiz/NADI-VirtualPatient with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Faris-Faiz/NADI-VirtualPatient with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Faris-Faiz/NADI-VirtualPatient",
	filename="NADI-VirtualPatient.gguf",
)

llm.create_chat_completion(
	messages = "{\n    \"question\": \"What is my name?\",\n    \"context\": \"My name is Clara and I live in Berkeley.\"\n}"
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Faris-Faiz/NADI-VirtualPatient with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Faris-Faiz/NADI-VirtualPatient
# Run inference directly in the terminal:
llama-cli -hf Faris-Faiz/NADI-VirtualPatient

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Faris-Faiz/NADI-VirtualPatient
# Run inference directly in the terminal:
llama-cli -hf Faris-Faiz/NADI-VirtualPatient

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 Faris-Faiz/NADI-VirtualPatient
# Run inference directly in the terminal:
./llama-cli -hf Faris-Faiz/NADI-VirtualPatient

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 Faris-Faiz/NADI-VirtualPatient
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Faris-Faiz/NADI-VirtualPatient

Use Docker

docker model run hf.co/Faris-Faiz/NADI-VirtualPatient

LM Studio
Jan
Ollama
How to use Faris-Faiz/NADI-VirtualPatient with Ollama:
```
ollama run hf.co/Faris-Faiz/NADI-VirtualPatient
```

Unsloth Studio new

How to use Faris-Faiz/NADI-VirtualPatient 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 Faris-Faiz/NADI-VirtualPatient 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 Faris-Faiz/NADI-VirtualPatient to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Faris-Faiz/NADI-VirtualPatient to start chatting

Pi new

How to use Faris-Faiz/NADI-VirtualPatient with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Faris-Faiz/NADI-VirtualPatient

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Faris-Faiz/NADI-VirtualPatient"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Faris-Faiz/NADI-VirtualPatient with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Faris-Faiz/NADI-VirtualPatient

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default Faris-Faiz/NADI-VirtualPatient

Run Hermes

hermes

Docker Model Runner
How to use Faris-Faiz/NADI-VirtualPatient with Docker Model Runner:
```
docker model run hf.co/Faris-Faiz/NADI-VirtualPatient
```

Lemonade

How to use Faris-Faiz/NADI-VirtualPatient with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Faris-Faiz/NADI-VirtualPatient

Run and chat with the model

lemonade run user.NADI-VirtualPatient-{{QUANT_TAG}}

List all available models

lemonade list

Model Card for Model ID

This model has been created using proprietary data, sourced from Universiti Kebangsaan Malaysia (UKM)

Model Details

Model Description

Developed by: Faris Faiz
Model type: GGUF
Language(s) (NLP): [More Information Needed]
License: [More Information Needed]
Finetuned from model [optional]: Malaysian Llama 3.1 8B Instruct v0.1

Uses

Direct Use

Sample prompt template:

ANDA ADALAH PESAKIT. ANDA BUKAN DOKTOR.

KLINIK: <put urself brah>
PROFIL PESAKIT:
<put urself brah>
Diagnosis klinikal: <put urself brah>
Topik perubatan: <put urself brah>

Peraturan ringkas:
- Jawab sebagai PESAKIT sahaja, bukan doktor.
- Guna 'saya' untuk diri sendiri dan 'doktor' untuk pelajar.
- Jawapan dalam Bahasa Malaysia harian.
- Elakkan istilah medik yang rumit bila bercakap dengan doktor."

Out-of-Scope Use

Don't use this to diagnose people with medical illnessses.

Downloads last month: 6

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for Faris-Faiz/NADI-VirtualPatient

Base model

mesolitica/Malaysian-Llama-3.1-8B-Instruct-v0.1

Quantized

(2)

this model