Instructions to use KoboldAI/GPT-NeoX-20B-Skein with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KoboldAI/GPT-NeoX-20B-Skein with Transformers:

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

pipe = pipeline("text-generation", model="KoboldAI/GPT-NeoX-20B-Skein")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("KoboldAI/GPT-NeoX-20B-Skein")
model = AutoModelForCausalLM.from_pretrained("KoboldAI/GPT-NeoX-20B-Skein")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use KoboldAI/GPT-NeoX-20B-Skein with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/KoboldAI/GPT-NeoX-20B-Skein

SGLang

How to use KoboldAI/GPT-NeoX-20B-Skein 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/GPT-NeoX-20B-Skein" \
    --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/GPT-NeoX-20B-Skein",
		"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/GPT-NeoX-20B-Skein" \
        --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/GPT-NeoX-20B-Skein",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use KoboldAI/GPT-NeoX-20B-Skein with Docker Model Runner:
```
docker model run hf.co/KoboldAI/GPT-NeoX-20B-Skein
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

GPT-NeoX-20B-Skein

Model description

Skein is a series of hybrid story generation models intended for use in both text adventure writing and normal novel-style writing. The models are known to possess a strong second person bias. For inquiries, please contact the KoboldAI community.

The name comes from the Integrated Development Environment for the Inform 7 programming language, which calls a dialogue tree a "skein". Inform 6 and 7 were used to create some of the interactive fiction in the dataset.

Training procedure

GPT-NeoX-20B-Skein was trained on a TPUv3-32 TPU pod using a heavily modified version of Ben Wang's Mesh Transformer JAX library, the original version of which was used by EleutherAI to train their GPT-J-6B model. The training hyperparameters and statistics can be found here.

Training data

The data are mostly comprised of light novels from the dataset of the KoboldAI/GPT-Neo-2.7B-Horni-LN model and assorted interactive fiction. The dataset uses [Themes: <comma-separated list of genres>] for tagging. For more details, consult this document.

Limitations and biases

Based on known problems with NLP technology, potential relevant factors include bias (gender, profession, race and religion).

Citation details

The GPT-NeoX-20B model weights:

@inproceedings{gpt-neox-20b,
  title={{GPT-NeoX-20B}: An Open-Source Autoregressive Language Model},
  author={Black, Sid and Biderman, Stella and Hallahan, Eric and Anthony, Quentin and Gao, Leo and Golding, Laurence and He, Horace and Leahy, Connor and McDonell, Kyle and Phang, Jason and Pieler, Michael and Prashanth, USVSN Sai and Purohit, Shivanshu and Reynolds, Laria and Tow, Jonathan and Wang, Ben and Weinbach, Samuel},
  booktitle={Proceedings of the ACL Workshop on Challenges \& Perspectives in Creating Large Language Models},
  url={https://arxiv.org/abs/2204.06745},
  year={2022}
}

The Mesh Transformer JAX library:

@misc{mesh-transformer-jax,
  author = {Wang, Ben},
  title = {{Mesh-Transformer-JAX: Model-Parallel Implementation of Transformer Language Model with JAX}},
  howpublished = {\url{https://github.com/kingoflolz/mesh-transformer-jax}},
  year = 2021,
  month = May
}

Downloads last month: 1,815

Model tree for KoboldAI/GPT-NeoX-20B-Skein

Quantizations

2 models

Spaces using KoboldAI/GPT-NeoX-20B-Skein 33

Paper for KoboldAI/GPT-NeoX-20B-Skein

GPT-NeoX-20B: An Open-Source Autoregressive Language Model

Paper • 2204.06745 • Published Apr 14, 2022 • 1