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

Libraries

How to use UniLLMer/MagMelKaa with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("UniLLMer/MagMelKaa", dtype="auto")

llama-cpp-python

How to use UniLLMer/MagMelKaa with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="UniLLMer/MagMelKaa",
	filename="R16432Kaaall.Q5_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 UniLLMer/MagMelKaa with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf UniLLMer/MagMelKaa:Q5_K_M
# Run inference directly in the terminal:
llama-cli -hf UniLLMer/MagMelKaa:Q5_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf UniLLMer/MagMelKaa:Q5_K_M
# Run inference directly in the terminal:
llama-cli -hf UniLLMer/MagMelKaa:Q5_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 UniLLMer/MagMelKaa:Q5_K_M
# Run inference directly in the terminal:
./llama-cli -hf UniLLMer/MagMelKaa:Q5_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 UniLLMer/MagMelKaa:Q5_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf UniLLMer/MagMelKaa:Q5_K_M

Use Docker

docker model run hf.co/UniLLMer/MagMelKaa:Q5_K_M

LM Studio
Jan
Ollama
How to use UniLLMer/MagMelKaa with Ollama:
```
ollama run hf.co/UniLLMer/MagMelKaa:Q5_K_M
```

Unsloth Studio new

How to use UniLLMer/MagMelKaa 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 UniLLMer/MagMelKaa 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 UniLLMer/MagMelKaa to start chatting

Using HuggingFace Spaces for Unsloth

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

Docker Model Runner
How to use UniLLMer/MagMelKaa with Docker Model Runner:
```
docker model run hf.co/UniLLMer/MagMelKaa:Q5_K_M
```

Lemonade

How to use UniLLMer/MagMelKaa with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull UniLLMer/MagMelKaa:Q5_K_M

Run and chat with the model

lemonade run user.MagMelKaa-Q5_K_M

List all available models

lemonade list

Uploaded model

Developed by: UniLLMer
License: apache-2.0
Finetuned from model : inflatebot/MN-12B-Mag-Mell-R1

This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month: 16

GGUF

Model size

12B params

Architecture

llama

Hardware compatibility

5-bit

Inference Providers NEW

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

Model tree for UniLLMer/MagMelKaa

Base model

inflatebot/MN-12B-Mag-Mell-R1

Quantized

(24)

this model