Instructions to use Kooten/DaringMaid-20B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Kooten/DaringMaid-20B-GGUF 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 Kooten/DaringMaid-20B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Kooten/DaringMaid-20B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Kooten/DaringMaid-20B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Kooten/DaringMaid-20B-GGUF: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 Kooten/DaringMaid-20B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Kooten/DaringMaid-20B-GGUF: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 Kooten/DaringMaid-20B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Kooten/DaringMaid-20B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Kooten/DaringMaid-20B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Kooten/DaringMaid-20B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kooten/DaringMaid-20B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kooten/DaringMaid-20B-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Kooten/DaringMaid-20B-GGUF:Q4_K_M

Ollama
How to use Kooten/DaringMaid-20B-GGUF with Ollama:
```
ollama run hf.co/Kooten/DaringMaid-20B-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use Kooten/DaringMaid-20B-GGUF with Docker Model Runner:
```
docker model run hf.co/Kooten/DaringMaid-20B-GGUF:Q4_K_M
```

Lemonade

How to use Kooten/DaringMaid-20B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Kooten/DaringMaid-20B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.DaringMaid-20B-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

This repo contains GGUF quants of DaringMaid-20B

New quants: IQ2-XS, IQ2-XXS

Q3_K_M - Q4_K_M - Q5_K_M

DaringMaid-20B

My goal was to make a Noromaid that's smarter and better at following instructions.

After trying a bunch of different recipes I think this one turned out pretty good

I used sequelbox/DynamicFactor as a base to as its supposed "improve overall knowledge, precise communication, conceptual understanding, and technical skill" over the base llama2.
NeverSleep/Noromaid of course.
Undi95/Utopia has been recommended again recently and its still really good so in the mixer it goes
I enjoyed tavtav/Rose so i threw in a bit of CalderaAI/Thorns
There was recently a model that tried to pass itself off as Gryphe/MythoMax, i made a merge with that model before it was revealed to be MythoMax and it turned out pretty good so i used it.

The .yml config files for mergekit with the exact merges can be found in the "Recipe" folder in the fp16 repo

Quants

GGUF, EXL2: 6bpw, 3bpw

Prompt template:

I have been using Undi/Ikaris SillyTavern presets for Noromaid: Context, Instruct.

Alpaca:

Below is an instruction that describes a task. Write a response that appropriately completes the request. Do not include descriptions of non-visual qualities such as personality, movements, scents, mental traits, or anything which could not be seen in a still photograph. Do not write in full sentences. Prefix your description with the phrase 'full body portrait,'

### Instruction:
{prompt}

### Response:

Downloads last month: 388

GGUF

Model size

20B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

Collection including Kooten/DaringMaid-20B-GGUF

IQ2 IMatrix GGUF

Collection

Tiny quants • 7 items • Updated Feb 8, 2024 • 1