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

Libraries

How to use Gryphe/MergeMonster with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Gryphe/MergeMonster",
	filename="MergeMonster-13b-20231124.q4_K_M.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Gryphe/MergeMonster with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Gryphe/MergeMonster:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Gryphe/MergeMonster:Q4_K_M

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/Gryphe/MergeMonster:Q4_K_M

LM Studio
Jan
Ollama
How to use Gryphe/MergeMonster with Ollama:
```
ollama run hf.co/Gryphe/MergeMonster:Q4_K_M
```

Unsloth Studio new

How to use Gryphe/MergeMonster 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 Gryphe/MergeMonster 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 Gryphe/MergeMonster to start chatting

Using HuggingFace Spaces for Unsloth

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

Docker Model Runner
How to use Gryphe/MergeMonster with Docker Model Runner:
```
docker model run hf.co/Gryphe/MergeMonster:Q4_K_M
```

Lemonade

How to use Gryphe/MergeMonster with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Gryphe/MergeMonster:Q4_K_M

Run and chat with the model

lemonade run user.MergeMonster-Q4_K_M

List all available models

lemonade list

MergeMonster

An unsupervised merging algorithm for Transformers-based language models, using a list of phrases (both good and bad) and a fully automated strategy that strives to decrease (or increase) the probability of these phrases occurring in the final merge.

Code available here

This repo serves as a place to store various promising quantizations of merges produced by the Merge Monster.

Current variations

MergeMonster-7b - First model: Mistral 0.1, with the objective to reduce overused GPT style roleplaying phrases.
MergeMonster-13b - First model: MythoMax, with the objective to reduce overused GPT style roleplaying phrases.
MergeMonster-Decensored-7b - First model: Mistral 0.1, with the objective to reduce refusals on a global level.
MergeMonster-Decensored-13b - First model: MythoMax, with the objective to reduce refusals on a global level.
MergeMonster-WritingStyle-7b - First model: Mistral 0.1, with the singular goal to increase the chance of completing a nicely written roleplaying paragraph.

Downloads last month: 111

GGUF

Model size

13B params

Architecture

llama

Hardware compatibility

4-bit

5-bit

6-bit

Inference Providers NEW

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