Instructions to use CorticalStack/shadow-clown-7B-dare with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CorticalStack/shadow-clown-7B-dare with Transformers:

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

pipe = pipeline("text-generation", model="CorticalStack/shadow-clown-7B-dare")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CorticalStack/shadow-clown-7B-dare")
model = AutoModelForCausalLM.from_pretrained("CorticalStack/shadow-clown-7B-dare", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CorticalStack/shadow-clown-7B-dare with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CorticalStack/shadow-clown-7B-dare"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CorticalStack/shadow-clown-7B-dare",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/CorticalStack/shadow-clown-7B-dare

SGLang

How to use CorticalStack/shadow-clown-7B-dare 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 "CorticalStack/shadow-clown-7B-dare" \
    --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": "CorticalStack/shadow-clown-7B-dare",
		"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 "CorticalStack/shadow-clown-7B-dare" \
        --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": "CorticalStack/shadow-clown-7B-dare",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use CorticalStack/shadow-clown-7B-dare with Docker Model Runner:
```
docker model run hf.co/CorticalStack/shadow-clown-7B-dare
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

shadow-clown-7B-dare

shadow-clown-7B-dare is a DARE merge of the following models using mergekit:

See the paper Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch for more on the method.

🧩 Configuration

models:
  - model: yam-peleg/Experiment26-7B
  - model: CorticalStack/pastiche-crown-clown-7b-dare-dpo
    parameters:
      density: 0.52
      weight: 0.4
  - model: CultriX/NeuralTrix-7B-dpo
    parameters:
      density: 0.52
      weight: 0.2
  - model: CorticalStack/neurotic-crown-clown-7b-ties
    parameters:
      density: 0.52
      weight: 0.3
merge_method: dare_ties
base_model: yam-peleg/Experiment26-7B
parameters:
  int8_mask: true
dtype: bfloat16

Downloads last month: 57

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for CorticalStack/shadow-clown-7B-dare

Merges

4 models

Quantizations

2 models

Paper for CorticalStack/shadow-clown-7B-dare

Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch

Paper • 2311.03099 • Published Nov 6, 2023 • 36