Instructions to use whyhow-ai/PatientSeek with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use whyhow-ai/PatientSeek with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="whyhow-ai/PatientSeek",
	filename="snapshots/70661aa9b9e6c69734b394916ddbc540fd4731bf/DeepSeek-R1-Distill-Llama-8B-Q4_K_M.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 whyhow-ai/PatientSeek with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf whyhow-ai/PatientSeek:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf whyhow-ai/PatientSeek:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf whyhow-ai/PatientSeek:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf whyhow-ai/PatientSeek: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 whyhow-ai/PatientSeek:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf whyhow-ai/PatientSeek: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 whyhow-ai/PatientSeek:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf whyhow-ai/PatientSeek:Q4_K_M

Use Docker

docker model run hf.co/whyhow-ai/PatientSeek:Q4_K_M

LM Studio
Jan
Ollama
How to use whyhow-ai/PatientSeek with Ollama:
```
ollama run hf.co/whyhow-ai/PatientSeek:Q4_K_M
```

Unsloth Studio new

How to use whyhow-ai/PatientSeek 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 whyhow-ai/PatientSeek 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 whyhow-ai/PatientSeek to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for whyhow-ai/PatientSeek to start chatting

Docker Model Runner
How to use whyhow-ai/PatientSeek with Docker Model Runner:
```
docker model run hf.co/whyhow-ai/PatientSeek:Q4_K_M
```

Lemonade

How to use whyhow-ai/PatientSeek with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull whyhow-ai/PatientSeek:Q4_K_M

Run and chat with the model

lemonade run user.PatientSeek-Q4_K_M

List all available models

lemonade list

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

You agree to not use the model to conduct experiments that cause harm to human subjects.

Model Card for Model ID

This model has been finetuned on patient records from over 10,000 patients, with full histories. It's been specifically tuned on summarisation, basic QA for extraction, and reasoned hypothesis for causation for medical-legal usecases.

Model Details

Model Description

Developed by: whyhow.ai
Model type: DeepSeek R1 Distill Llama 8B
Article: https://medium.com/enterprise-rag/introducing-patientseek-the-first-open-source-med-legal-deepseek-reasoning-model-74f98e9608ae

Model Sources [optional]

Repository: https://huggingface.co/unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF

Uses

Used for summarising one to many medical records for patients, for basic QA of medical records, and for hypothesis testing in the form of associative reasoning.

How to Get Started with the Model

The best instructions on how to run are here: https://unsloth.ai/blog/deepseek-r1

Model Card Contact

Email us at team@whyhow.ai.

Downloads last month: 11

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

4-bit

Model tree for whyhow-ai/PatientSeek

Base model

deepseek-ai/DeepSeek-R1-Distill-Llama-8B

Quantized

unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF