Instructions to use athirdpath/CleverGirl-20b-Blended-v1.1-DARE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use athirdpath/CleverGirl-20b-Blended-v1.1-DARE with Transformers:

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

pipe = pipeline("text-generation", model="athirdpath/CleverGirl-20b-Blended-v1.1-DARE")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("athirdpath/CleverGirl-20b-Blended-v1.1-DARE")
model = AutoModelForCausalLM.from_pretrained("athirdpath/CleverGirl-20b-Blended-v1.1-DARE", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use athirdpath/CleverGirl-20b-Blended-v1.1-DARE with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "athirdpath/CleverGirl-20b-Blended-v1.1-DARE"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "athirdpath/CleverGirl-20b-Blended-v1.1-DARE",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/athirdpath/CleverGirl-20b-Blended-v1.1-DARE

SGLang

How to use athirdpath/CleverGirl-20b-Blended-v1.1-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 "athirdpath/CleverGirl-20b-Blended-v1.1-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": "athirdpath/CleverGirl-20b-Blended-v1.1-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 "athirdpath/CleverGirl-20b-Blended-v1.1-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": "athirdpath/CleverGirl-20b-Blended-v1.1-DARE",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use athirdpath/CleverGirl-20b-Blended-v1.1-DARE with Docker Model Runner:
```
docker model run hf.co/athirdpath/CleverGirl-20b-Blended-v1.1-DARE
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Description

After I put down the joint and RTFM, I have a better idea exactly what's going on. I considered doing something similar with WANDA or SparseGPT a while back, but stopped when I ran into issues. Thus, I'm fascinated by this new method's execution.

Hypothesis

By lowering the density, I hit closer to the sweet-spot shown in the paper. Also, I'm using my fixed base model, so hopefully that helps too. Weights are adjusted to make the later layers more aligned with ORCA 2.

Results

I'm quite happy with this model for what it is, a personable and effective assistant. It does infodump a bit, but what genius doesn't? It writes okay erotica and general fiction, it just has an "artifical" tone.