Instructions to use Echelon-AI/Med-Qwen2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Echelon-AI/Med-Qwen2-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Echelon-AI/Med-Qwen2-GGUF",
	filename="unsloth.BF16.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Echelon-AI/Med-Qwen2-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Echelon-AI/Med-Qwen2-GGUF:BF16
# Run inference directly in the terminal:
llama-cli -hf Echelon-AI/Med-Qwen2-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Echelon-AI/Med-Qwen2-GGUF:BF16
# Run inference directly in the terminal:
llama-cli -hf Echelon-AI/Med-Qwen2-GGUF:BF16

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 Echelon-AI/Med-Qwen2-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf Echelon-AI/Med-Qwen2-GGUF:BF16

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 Echelon-AI/Med-Qwen2-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Echelon-AI/Med-Qwen2-GGUF:BF16

Use Docker

docker model run hf.co/Echelon-AI/Med-Qwen2-GGUF:BF16

LM Studio
Jan
Ollama
How to use Echelon-AI/Med-Qwen2-GGUF with Ollama:
```
ollama run hf.co/Echelon-AI/Med-Qwen2-GGUF:BF16
```

Unsloth Studio

How to use Echelon-AI/Med-Qwen2-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 Echelon-AI/Med-Qwen2-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 Echelon-AI/Med-Qwen2-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Echelon-AI/Med-Qwen2-GGUF to start chatting

Docker Model Runner
How to use Echelon-AI/Med-Qwen2-GGUF with Docker Model Runner:
```
docker model run hf.co/Echelon-AI/Med-Qwen2-GGUF:BF16
```

Lemonade

How to use Echelon-AI/Med-Qwen2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Echelon-AI/Med-Qwen2-GGUF:BF16

Run and chat with the model

lemonade run user.Med-Qwen2-GGUF-BF16

List all available models

lemonade list

Qwen2 7B, after finetuning on a medical dataset, demonstrates enhanced performance in medical text understanding and generation

Model Description

The model shows improved accuracy in diagnosing medical conditions, generating specialized medical texts, and responding to medical queries with contextually relevant information. This adaptation equips Med-Qwen2 to support advanced applications in healthcare, offering nuanced insights and precise language processing tailored for medical professionals and patients alike

Finetuned from model : https://huggingface.co/Qwen/Qwen2-7B-Instruct

Uses

Diagnosing medical conditions with improved accuracy.
Generating specialized medical texts and reports.
Providing contextually relevant responses to medical queries.
Supporting advanced applications in healthcare with precise language processing.

Sample Outputs:

Downloads last month: 79

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

5-bit

8-bit

16-bit

Inference Providers NEW

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