Instructions to use athirdpath/PivotMaid-11b-DARE_TIES with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use athirdpath/PivotMaid-11b-DARE_TIES with Transformers:

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

pipe = pipeline("text-generation", model="athirdpath/PivotMaid-11b-DARE_TIES")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("athirdpath/PivotMaid-11b-DARE_TIES")
model = AutoModelForCausalLM.from_pretrained("athirdpath/PivotMaid-11b-DARE_TIES")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use athirdpath/PivotMaid-11b-DARE_TIES with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "athirdpath/PivotMaid-11b-DARE_TIES"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "athirdpath/PivotMaid-11b-DARE_TIES",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/athirdpath/PivotMaid-11b-DARE_TIES

SGLang

How to use athirdpath/PivotMaid-11b-DARE_TIES 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 "athirdpath/PivotMaid-11b-DARE_TIES" \
    --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": "athirdpath/PivotMaid-11b-DARE_TIES",
		"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 "athirdpath/PivotMaid-11b-DARE_TIES" \
        --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": "athirdpath/PivotMaid-11b-DARE_TIES",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use athirdpath/PivotMaid-11b-DARE_TIES with Docker Model Runner:
```
docker model run hf.co/athirdpath/PivotMaid-11b-DARE_TIES
```

What an oddly stubborn model.

4-bit Examples with Alpaca

!!NSFW!! - Erotica Writing Example - !!NSFW!!

While I like this NSFW output, I had to change my standard test prompt nearly a dozen times to get it to produce anything smut-like.

There were zero refusals, just sappy Young Adult romance nonsense.

Recipe

merge_method: dare_ties

base_model: athirdpath/BigMistral-11b
model: athirdpath/DoublePivot-11b

weight: [0.20, 0.34, 0.42, 0.53, 0.60] / density: 0.45
model: athirdpath/DoubleMaid-11b

weight: [0.65, 0.51, 0.43, 0.32, 0.25] / density: [0.60, 0.54, 0.50, 0.48, 0.40]
model: athirdpath/BigMistral-11b-GLUED

weight: 0.15 / density: 0.40

int8_mask: true

dtype: bfloat16

Downloads last month: 4

Safetensors

Model size

11B params

Tensor type

BF16