Instructions to use KoboldAI/OPT-13B-Nerybus-Mix with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KoboldAI/OPT-13B-Nerybus-Mix with Transformers:

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

pipe = pipeline("text-generation", model="KoboldAI/OPT-13B-Nerybus-Mix")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("KoboldAI/OPT-13B-Nerybus-Mix")
model = AutoModelForCausalLM.from_pretrained("KoboldAI/OPT-13B-Nerybus-Mix")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use KoboldAI/OPT-13B-Nerybus-Mix with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KoboldAI/OPT-13B-Nerybus-Mix"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KoboldAI/OPT-13B-Nerybus-Mix",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/KoboldAI/OPT-13B-Nerybus-Mix

SGLang

How to use KoboldAI/OPT-13B-Nerybus-Mix 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 "KoboldAI/OPT-13B-Nerybus-Mix" \
    --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": "KoboldAI/OPT-13B-Nerybus-Mix",
		"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 "KoboldAI/OPT-13B-Nerybus-Mix" \
        --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": "KoboldAI/OPT-13B-Nerybus-Mix",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use KoboldAI/OPT-13B-Nerybus-Mix with Docker Model Runner:
```
docker model run hf.co/KoboldAI/OPT-13B-Nerybus-Mix
```

OPT 13B - Nerybus Mix

Model description

This is a merged (50/50) model of both Erebus 13B and Nerys V2 13B by Mr. Seeker. Warning: THIS model is NOT suitable for use by minors. The model will output X-rated content.

Information:

For more information, check out the two source models:

Limitations and biases

Based on known problems with NLP technology, potential relevant factors include bias (gender, profession, race and religion). Warning: This model has a very strong NSFW bias!

License

BibTeX entry and citation info

@misc{zhang2022opt,
      title={OPT: Open Pre-trained Transformer Language Models}, 
      author={Susan Zhang and Stephen Roller and Naman Goyal and Mikel Artetxe and Moya Chen and Shuohui Chen and Christopher Dewan and Mona Diab and Xian Li and Xi Victoria Lin and Todor Mihaylov and Myle Ott and Sam Shleifer and Kurt Shuster and Daniel Simig and Punit Singh Koura and Anjali Sridhar and Tianlu Wang and Luke Zettlemoyer},
      year={2022},
      eprint={2205.01068},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

Downloads last month: 1,225

Spaces using KoboldAI/OPT-13B-Nerybus-Mix 31

Paper for KoboldAI/OPT-13B-Nerybus-Mix

OPT: Open Pre-trained Transformer Language Models

Paper • 2205.01068 • Published May 2, 2022 • 2