Instructions to use Mykes/med_chat_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Mykes/med_chat_model with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Mykes/med_chat_model",
	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

llama.cpp

How to use Mykes/med_chat_model with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Mykes/med_chat_model:BF16
# Run inference directly in the terminal:
llama-cli -hf Mykes/med_chat_model:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Mykes/med_chat_model:BF16
# Run inference directly in the terminal:
llama-cli -hf Mykes/med_chat_model: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 Mykes/med_chat_model:BF16
# Run inference directly in the terminal:
./llama-cli -hf Mykes/med_chat_model: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 Mykes/med_chat_model:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Mykes/med_chat_model:BF16

Use Docker

docker model run hf.co/Mykes/med_chat_model:BF16

LM Studio
Jan
Ollama
How to use Mykes/med_chat_model with Ollama:
```
ollama run hf.co/Mykes/med_chat_model:BF16
```

Unsloth Studio new

How to use Mykes/med_chat_model 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 Mykes/med_chat_model 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 Mykes/med_chat_model to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Mykes/med_chat_model to start chatting

Pi new

How to use Mykes/med_chat_model with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Mykes/med_chat_model:BF16

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": "Mykes/med_chat_model:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Mykes/med_chat_model with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Mykes/med_chat_model:BF16

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 Mykes/med_chat_model:BF16

Run Hermes

hermes

Docker Model Runner
How to use Mykes/med_chat_model with Docker Model Runner:
```
docker model run hf.co/Mykes/med_chat_model:BF16
```

Lemonade

How to use Mykes/med_chat_model with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Mykes/med_chat_model:BF16

Run and chat with the model

lemonade run user.med_chat_model-BF16

List all available models

lemonade list

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

System prompt:

Ты помощник. Перед ответом на вопрос ты обдумываешь ответ.\nТвои рассуждения пиши после ## Thinking.\nОтвет на вопрос после ## Final Response

Отказ от ответственности для языковой модели

Данная языковая модель предоставляется исключительно в образовательных и исследовательских целях. Разработчики модели и ее дистрибьюторы не несут ответственности за любые последствия, связанные с использованием этой модели. Модель может генерировать текст, содержащий неточную, неполную, устаревшую или потенциально оскорбительную информацию. Пользователь принимает на себя полную ответственность за использование этой модели и за любые действия, предпринятые на основе ее вывода. Модель не предназначена для использования в критически важных системах, включая медицинские, финансовые, правовые или другие области, где ошибки могут привести к значительному ущербу.

Используя эту модель, вы соглашаетесь с тем, что разработчики, дистрибьюторы и операторы платформы не будут нести ответственности за любые претензии, убытки или ущерб, возникшие в результате использования или невозможности использования этой модели.

This language model is provided solely for educational and research purposes. The developers and distributors of the model are not responsible for any consequences arising from the use of this model. The model may generate text that is inaccurate, incomplete, outdated, or potentially offensive. The user assumes full responsibility for the use of this model and any actions taken based on its output. The model is not intended for use in critical systems, including medical, financial, legal, or other domains where errors could result in significant harm.

By using this model, you agree that the developers, distributors, and platform operators shall not be held liable for any claims, losses, or damages arising from the use or inability to use this model.

Downloads last month: 7

Safetensors

Model size

8B params

Tensor type

BF16

Inference Providers NEW

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

Model tree for Mykes/med_chat_model

Quantizations

2 models