Instructions to use BotBot6990/Dirty-Muse-1-Million-Context with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use BotBot6990/Dirty-Muse-1-Million-Context with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf BotBot6990/Dirty-Muse-1-Million-Context:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf BotBot6990/Dirty-Muse-1-Million-Context:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf BotBot6990/Dirty-Muse-1-Million-Context:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf BotBot6990/Dirty-Muse-1-Million-Context: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 BotBot6990/Dirty-Muse-1-Million-Context:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf BotBot6990/Dirty-Muse-1-Million-Context: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 BotBot6990/Dirty-Muse-1-Million-Context:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf BotBot6990/Dirty-Muse-1-Million-Context:Q4_K_M

Use Docker

docker model run hf.co/BotBot6990/Dirty-Muse-1-Million-Context:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use BotBot6990/Dirty-Muse-1-Million-Context with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BotBot6990/Dirty-Muse-1-Million-Context"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BotBot6990/Dirty-Muse-1-Million-Context",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/BotBot6990/Dirty-Muse-1-Million-Context:Q4_K_M

Ollama
How to use BotBot6990/Dirty-Muse-1-Million-Context with Ollama:
```
ollama run hf.co/BotBot6990/Dirty-Muse-1-Million-Context:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use BotBot6990/Dirty-Muse-1-Million-Context with Docker Model Runner:
```
docker model run hf.co/BotBot6990/Dirty-Muse-1-Million-Context:Q4_K_M
```

Lemonade

How to use BotBot6990/Dirty-Muse-1-Million-Context with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull BotBot6990/Dirty-Muse-1-Million-Context:Q4_K_M

Run and chat with the model

lemonade run user.Dirty-Muse-1-Million-Context-Q4_K_M

List all available models

lemonade list

Atomic Chat

I have not extensively tested with long games, but with the testing I have done it seems to hold up well.

I extended the context to better handle games as the short context limit would end games quickly.

I advise testing the context to see what your system can handle.

All testing was done in Oobabooga TextGen. Results of my tests are as follows.

Context	Q4_K_M	TBA	TBA	TBA
100,000	7.4GB	TBA	TBA	TBA
250,000	34.2GB	TBA	TBA	TBA
500,000	79.9GB	TBA	TBA	TBA
750,000	125.5GB	TBA	TBA	TBA
1,000,000	175.1GB	TBA	TBA	TBA

I take no credit for the creation of this model.

Downloads last month: 611

GGUF

Model size

9B params

Architecture

gemma2

Hardware compatibility

4-bit

Model tree for BotBot6990/Dirty-Muse-1-Million-Context

Base model

Mantis2024/Dirty-Muse-Writer-v01-Uncensored-Erotica-NSFW

Quantized

(11)

this model