Instructions to use Heralax/Augmental-Unholy-Chai-Submission with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Heralax/Augmental-Unholy-Chai-Submission with Transformers:

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

pipe = pipeline("text-generation", model="Heralax/Augmental-Unholy-Chai-Submission")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Heralax/Augmental-Unholy-Chai-Submission")
model = AutoModelForCausalLM.from_pretrained("Heralax/Augmental-Unholy-Chai-Submission")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Heralax/Augmental-Unholy-Chai-Submission with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Heralax/Augmental-Unholy-Chai-Submission

SGLang

How to use Heralax/Augmental-Unholy-Chai-Submission 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 "Heralax/Augmental-Unholy-Chai-Submission" \
    --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": "Heralax/Augmental-Unholy-Chai-Submission",
		"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 "Heralax/Augmental-Unholy-Chai-Submission" \
        --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": "Heralax/Augmental-Unholy-Chai-Submission",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Heralax/Augmental-Unholy-Chai-Submission with Docker Model Runner:
```
docker model run hf.co/Heralax/Augmental-Unholy-Chai-Submission
```

Chai wasn't letting me point to the original Augmental Unholy model repo, so this is just that but with fewer files. Feel free to ignore, it's nothing new.

I've been working on an augmented data pipeline in the last few months, it's nearly there and I'm not dead!

Downloads last month: 3