Instructions to use Kooten/DaringMaid-13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kooten/DaringMaid-13B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Kooten/DaringMaid-13B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Kooten/DaringMaid-13B")
model = AutoModelForCausalLM.from_pretrained("Kooten/DaringMaid-13B")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Kooten/DaringMaid-13B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kooten/DaringMaid-13B"
# 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-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Kooten/DaringMaid-13B

SGLang

How to use Kooten/DaringMaid-13B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Kooten/DaringMaid-13B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kooten/DaringMaid-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Kooten/DaringMaid-13B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kooten/DaringMaid-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Kooten/DaringMaid-13B with Docker Model Runner:
```
docker model run hf.co/Kooten/DaringMaid-13B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

DaringMaid-13B

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 liked 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

EXL2: 8bpw, 5bpw, 4bpw

GGUF: Q3_K_M - Q4_K_M - Q5_K_M

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: