Instructions to use Gurubot/mellow-mate-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Gurubot/mellow-mate-8b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Gurubot/mellow-mate-8b",
	filename="mellow-mate-8b.Q4_K_M.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 Gurubot/mellow-mate-8b with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Gurubot/mellow-mate-8b:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Gurubot/mellow-mate-8b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Gurubot/mellow-mate-8b:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Gurubot/mellow-mate-8b: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 Gurubot/mellow-mate-8b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Gurubot/mellow-mate-8b: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 Gurubot/mellow-mate-8b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Gurubot/mellow-mate-8b:Q4_K_M

Use Docker

docker model run hf.co/Gurubot/mellow-mate-8b:Q4_K_M

LM Studio
Jan
Ollama
How to use Gurubot/mellow-mate-8b with Ollama:
```
ollama run hf.co/Gurubot/mellow-mate-8b:Q4_K_M
```

Unsloth Studio new

How to use Gurubot/mellow-mate-8b 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 Gurubot/mellow-mate-8b 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 Gurubot/mellow-mate-8b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Gurubot/mellow-mate-8b to start chatting

Docker Model Runner
How to use Gurubot/mellow-mate-8b with Docker Model Runner:
```
docker model run hf.co/Gurubot/mellow-mate-8b:Q4_K_M
```

Lemonade

How to use Gurubot/mellow-mate-8b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Gurubot/mellow-mate-8b:Q4_K_M

Run and chat with the model

lemonade run user.mellow-mate-8b-Q4_K_M

List all available models

lemonade list

Designed to mimic a friendly instant message chat with a friend who chats with you about what you are up to, and asks follow up questions to keep the conversation going. It writes informally and in single sentences rather than paragraphs about being a helpful assistant.

You can get it from the ollama library here https://ollama.com/gurubot/mellow-mate

Finetuned from llama 3.1 8b

Downloads last month: 32

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 Gurubot/mellow-mate-8b

Quantizations

2 models