Instructions to use AliNadhir/SINA-Medical-Reasoning-LLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AliNadhir/SINA-Medical-Reasoning-LLM with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AliNadhir/SINA-Medical-Reasoning-LLM",
	filename="SINA-Medical-Reasoning-LLM.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use AliNadhir/SINA-Medical-Reasoning-LLM with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AliNadhir/SINA-Medical-Reasoning-LLM
# Run inference directly in the terminal:
llama-cli -hf AliNadhir/SINA-Medical-Reasoning-LLM

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AliNadhir/SINA-Medical-Reasoning-LLM
# Run inference directly in the terminal:
llama-cli -hf AliNadhir/SINA-Medical-Reasoning-LLM

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 AliNadhir/SINA-Medical-Reasoning-LLM
# Run inference directly in the terminal:
./llama-cli -hf AliNadhir/SINA-Medical-Reasoning-LLM

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 AliNadhir/SINA-Medical-Reasoning-LLM
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AliNadhir/SINA-Medical-Reasoning-LLM

Use Docker

docker model run hf.co/AliNadhir/SINA-Medical-Reasoning-LLM

LM Studio
Jan
Ollama
How to use AliNadhir/SINA-Medical-Reasoning-LLM with Ollama:
```
ollama run hf.co/AliNadhir/SINA-Medical-Reasoning-LLM
```

Unsloth Studio new

How to use AliNadhir/SINA-Medical-Reasoning-LLM 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 AliNadhir/SINA-Medical-Reasoning-LLM 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 AliNadhir/SINA-Medical-Reasoning-LLM to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AliNadhir/SINA-Medical-Reasoning-LLM to start chatting

Pi new

How to use AliNadhir/SINA-Medical-Reasoning-LLM with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf AliNadhir/SINA-Medical-Reasoning-LLM

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": "AliNadhir/SINA-Medical-Reasoning-LLM"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use AliNadhir/SINA-Medical-Reasoning-LLM with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf AliNadhir/SINA-Medical-Reasoning-LLM

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 AliNadhir/SINA-Medical-Reasoning-LLM

Run Hermes

hermes

Docker Model Runner
How to use AliNadhir/SINA-Medical-Reasoning-LLM with Docker Model Runner:
```
docker model run hf.co/AliNadhir/SINA-Medical-Reasoning-LLM
```

Lemonade

How to use AliNadhir/SINA-Medical-Reasoning-LLM with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AliNadhir/SINA-Medical-Reasoning-LLM

Run and chat with the model

lemonade run user.SINA-Medical-Reasoning-LLM-{{QUANT_TAG}}

List all available models

lemonade list

🧠 SINA Medical Reasoning LLM (Fine-Tuned by Ali Nadhir)

🚀 Model Overview

SINA Medical Reasoning LLM is a fine-tuned version of Qwen2.5-7B, developed specifically for advanced medical diagnostic reasoning. By incorporating Chain of Thought (CoT) methodologies, the model is designed to perform step-by-step clinical analysis and decision-making.

Inspired by the legacy of Ibn Sina (Avicenna), this model merges classical medical reasoning principles with the capabilities of large language models.

🔧 Fine-Tuning Details Base Model: Qwen2.5-7B

Fine-tuned by: Ali Nadhir

Library: Hugging Face Transformers using Unsloth

Dataset: FreedomIntelligence/medical-o1-reasoning-SFT

Hardware: 1× NVIDIA A100 (40GB VRAM)

Objective: Equip a non-reasoning LLM with structured medical reasoning capabilities to support accurate and explainable clinical inference.

📈 Reasoning Capabilities & Use Cases

Fine-tuning with Chain of Thought examples from a medical domain enables the model to improve performance in:

🩺 Differential diagnosis and symptom analysis

🧠 Multi-step clinical reasoning and logic chaining

📋 Structured Q&A in medical consultations

🧩 Educational simulations and AI-assisted diagnosis

Ideal for:

Clinical AI prototypes

Healthcare research and experimentation

MedEd (Medical Education) tools

Diagnostic reasoning assistants

🔐 Note: This release includes only the 4-bit quantized (4Q) version of the model, optimized for resource-constrained deployment.

Downloads last month: 5

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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

Model tree for AliNadhir/SINA-Medical-Reasoning-LLM

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Quantized

(311)

this model

AliNadhir
/

SINA-Medical-Reasoning-LLM